jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
Myhs-phz 2025-03-24 10:15:34 +00:00
parent 4f07a1c457
commit 199052e92e
33 changed files with 695 additions and 2026 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
opencompass/configs/datasets/IFEval/IFEval_gen.py
View File

@ -1,33 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import IFEvalDataset, IFEvaluator
from mmengine.config import read_base
ifeval_reader_cfg = dict(
input_columns=['prompt'], output_column='reference')
ifeval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt='{prompt}'),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
ifeval_eval_cfg = dict(
evaluator=dict(type=IFEvaluator),
pred_role='BOT',
)
ifeval_datasets = [
dict(
abbr='IFEval',
type=IFEvalDataset,
path='data/ifeval/input_data.jsonl',
reader_cfg=ifeval_reader_cfg,
infer_cfg=ifeval_infer_cfg,
eval_cfg=ifeval_eval_cfg)
]
with read_base():
from .IFEval_gen_353ae7 import ifeval_datasets # noqa: F401, F403

42
opencompass/configs/datasets/aime2024/aime2024_gen.py
View File

@ -1,40 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import Aime2024Dataset, MATHEvaluator, math_postprocess_v2
from opencompass.datasets import CustomDataset
from mmengine.config import read_base
aime2024_reader_cfg = dict(
input_columns=['question'],
output_column='answer'
)
aime2024_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{question}\nPlease reason step by step, and put your final answer within \\boxed{}.'),
],
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer)
)
aime2024_eval_cfg = dict(
evaluator=dict(type=MATHEvaluator, version='v2'), pred_postprocessor=dict(type=math_postprocess_v2)
)
aime2024_datasets = [
dict(
abbr='aime2024',
type=CustomDataset,
path='opencompass/aime2025',
reader_cfg=aime2024_reader_cfg,
infer_cfg=aime2024_infer_cfg,
eval_cfg=aime2024_eval_cfg,
)
]
with read_base():
from .aime2024_gen_17d799 import aime2024_datasets # noqa: F401, F403

40
opencompass/configs/datasets/aime2024/aime2024_gen_17d799.py Normal file
View File

@ -0,0 +1,40 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import Aime2024Dataset, MATHEvaluator, math_postprocess_v2
from opencompass.datasets import CustomDataset
aime2024_reader_cfg = dict(
input_columns=['question'],
output_column='answer'
)
aime2024_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{question}\nPlease reason step by step, and put your final answer within \\boxed{}.'),
],
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer)
)
aime2024_eval_cfg = dict(
evaluator=dict(type=MATHEvaluator, version='v2'), pred_postprocessor=dict(type=math_postprocess_v2)
)
aime2024_datasets = [
dict(
abbr='aime2024',
type=CustomDataset,
path='opencompass/aime2025',
reader_cfg=aime2024_reader_cfg,
infer_cfg=aime2024_infer_cfg,
eval_cfg=aime2024_eval_cfg,
)
]

86
opencompass/configs/datasets/aime2024/aime2024_llm_judge_gen.py
View File

@ -1,84 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import CustomDataset
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from mmengine.config import read_base
aime2024_reader_cfg = dict(input_columns=['question'], output_column='answer')
aime2024_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(
role='HUMAN',
prompt='{question}\nRemember to put your final answer within \\boxed{}.',
),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n{question}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
aime2024_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.",
)
],
round=[
dict(role='HUMAN', prompt=GRADER_TEMPLATE),
],
),
),
dataset_cfg=dict(
type=CustomDataset,
path='opencompass/aime2025',
reader_cfg=aime2024_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
)
)
aime2024_datasets = [
dict(
abbr='aime2024',
type=CustomDataset,
path='opencompass/aime2025',
reader_cfg=aime2024_reader_cfg,
infer_cfg=aime2024_infer_cfg,
eval_cfg=aime2024_eval_cfg,
)
]
with read_base():
from .aime2024_llmjudge_gen_5e9f4f import aime2024_datasets # noqa: F401, F403

102
opencompass/configs/datasets/bbh/bbh_gen.py
View File

@ -1,100 +1,4 @@
import os
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import BBHDataset, BBHEvaluator, bbh_mcq_postprocess, BBHEvaluator_mcq
bbh_reader_cfg = dict(input_columns=['input'], output_column='target')
bbh_multiple_choice_sets = [
'temporal_sequences',
'disambiguation_qa',
'date_understanding',
'tracking_shuffled_objects_three_objects',
'penguins_in_a_table',
'geometric_shapes',
'snarks',
'ruin_names',
'tracking_shuffled_objects_seven_objects',
'tracking_shuffled_objects_five_objects',
'logical_deduction_three_objects',
'hyperbaton',
'logical_deduction_five_objects',
'logical_deduction_seven_objects',
'movie_recommendation',
'salient_translation_error_detection',
'reasoning_about_colored_objects',
]
bbh_free_form_sets = [
'multistep_arithmetic_two',
'navigate',
'dyck_languages',
'word_sorting',
'sports_understanding',
'boolean_expressions',
'object_counting',
'formal_fallacies',
'causal_judgement',
'web_of_lies',
]
bbh_datasets = []
for _name in bbh_multiple_choice_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(
evaluator=dict(type=BBHEvaluator_mcq),
pred_role='BOT',
pred_postprocessor=dict(type=bbh_mcq_postprocess),
dataset_postprocessor=dict(type=bbh_mcq_postprocess))
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))
for _name in bbh_free_form_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(evaluator=dict(type=BBHEvaluator), pred_role='BOT')
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))
from mmengine.config import read_base
with read_base():
from .bbh_gen_ee62e9 import bbh_datasets # noqa: F401, F403

99
opencompass/configs/datasets/bbh/bbh_gen_ee62e9.py Normal file
View File

@ -0,0 +1,99 @@
import os
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import BBHDataset, BBHEvaluator, bbh_mcq_postprocess, BBHEvaluator_mcq
bbh_reader_cfg = dict(input_columns=['input'], output_column='target')
bbh_multiple_choice_sets = [
'temporal_sequences',
'disambiguation_qa',
'date_understanding',
'tracking_shuffled_objects_three_objects',
'penguins_in_a_table',
'geometric_shapes',
'snarks',
'ruin_names',
'tracking_shuffled_objects_seven_objects',
'tracking_shuffled_objects_five_objects',
'logical_deduction_three_objects',
'hyperbaton',
'logical_deduction_five_objects',
'logical_deduction_seven_objects',
'movie_recommendation',
'salient_translation_error_detection',
'reasoning_about_colored_objects',
]
bbh_free_form_sets = [
'multistep_arithmetic_two',
'navigate',
'dyck_languages',
'word_sorting',
'sports_understanding',
'boolean_expressions',
'object_counting',
'formal_fallacies',
'causal_judgement',
'web_of_lies',
]
bbh_datasets = []
for _name in bbh_multiple_choice_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(
evaluator=dict(type=BBHEvaluator_mcq),
pred_role='BOT',
pred_postprocessor=dict(type=bbh_mcq_postprocess),
dataset_postprocessor=dict(type=bbh_mcq_postprocess))
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))
for _name in bbh_free_form_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(evaluator=dict(type=BBHEvaluator), pred_role='BOT')
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))

182
opencompass/configs/datasets/bbh/bbh_llm_judge_gen.py
View File

@ -1,180 +1,4 @@
import os
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import BBHDataset, BBHEvaluator, bbh_mcq_postprocess, BBHEvaluator_mcq, generic_llmjudge_postprocess
from opencompass.evaluator import GenericLLMEvaluator
from mmengine.config import read_base
bbh_reader_cfg = dict(input_columns=['input'], output_column='target')
bbh_multiple_choice_sets = [
'temporal_sequences',
'disambiguation_qa',
'date_understanding',
'tracking_shuffled_objects_three_objects',
'penguins_in_a_table',
'geometric_shapes',
'snarks',
'ruin_names',
'tracking_shuffled_objects_seven_objects',
'tracking_shuffled_objects_five_objects',
'logical_deduction_three_objects',
'hyperbaton',
'logical_deduction_five_objects',
'logical_deduction_seven_objects',
'movie_recommendation',
'salient_translation_error_detection',
'reasoning_about_colored_objects',
]
bbh_free_form_sets = [
'multistep_arithmetic_two',
'navigate',
'dyck_languages',
'word_sorting',
'sports_understanding',
'boolean_expressions',
'object_counting',
'formal_fallacies',
'causal_judgement',
'web_of_lies',
]
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {question}\n {options_str} \n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
bbh_datasets = []
for _name in bbh_multiple_choice_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=BBHDataset,
path='opencompass/bbh',
reader_cfg=bbh_reader_cfg,
name=_name,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))
for _name in bbh_free_form_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt=GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=BBHDataset,
path='opencompass/bbh',
reader_cfg=bbh_reader_cfg,
name=_name,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))
with read_base():
from .bbh_llmjudge_gen_ee62e9 import bbh_datasets # noqa: F401, F403

180
opencompass/configs/datasets/bbh/bbh_llmjudge_gen_ee62e9.py Normal file
View File

@ -0,0 +1,180 @@
import os
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import BBHDataset, BBHEvaluator, bbh_mcq_postprocess, BBHEvaluator_mcq, generic_llmjudge_postprocess
from opencompass.evaluator import GenericLLMEvaluator
bbh_reader_cfg = dict(input_columns=['input'], output_column='target')
bbh_multiple_choice_sets = [
'temporal_sequences',
'disambiguation_qa',
'date_understanding',
'tracking_shuffled_objects_three_objects',
'penguins_in_a_table',
'geometric_shapes',
'snarks',
'ruin_names',
'tracking_shuffled_objects_seven_objects',
'tracking_shuffled_objects_five_objects',
'logical_deduction_three_objects',
'hyperbaton',
'logical_deduction_five_objects',
'logical_deduction_seven_objects',
'movie_recommendation',
'salient_translation_error_detection',
'reasoning_about_colored_objects',
]
bbh_free_form_sets = [
'multistep_arithmetic_two',
'navigate',
'dyck_languages',
'word_sorting',
'sports_understanding',
'boolean_expressions',
'object_counting',
'formal_fallacies',
'causal_judgement',
'web_of_lies',
]
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {question}\n {options_str} \n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
bbh_datasets = []
for _name in bbh_multiple_choice_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=BBHDataset,
path='opencompass/bbh',
reader_cfg=bbh_reader_cfg,
name=_name,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))
for _name in bbh_free_form_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=
f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
bbh_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt=GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=BBHDataset,
path='opencompass/bbh',
reader_cfg=bbh_reader_cfg,
name=_name,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))

48
opencompass/configs/datasets/bigcodebench/bigcodebench_gen.py
View File

@ -1,46 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import (BigCodeBenchDataset, BigCodeBenchEvaluator)
from mmengine.config import read_base
bigcodebench_hard_reader_cfg = dict(
input_columns=['instruct_prompt'],
output_column='test',
)
bigcodebench_hard_infer_cfg = dict(prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[dict(role='system', fallback_role='HUMAN', prompt='')],
round=[
dict(role='HUMAN', prompt='{instruct_prompt}'),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer,)
)
bigcodebench_hard_eval_cfg = dict(
evaluator=dict(
type=BigCodeBenchEvaluator,
release_version='v0.1.2',
eval_type='instruct',
# remote_execute_api='https://bigcode-bigcodebench-evaluator.hf.space/',
remote_execute_api=
'https://opencompass-opencompass-bigcodebench-evaluator.hf.space', # noqa: E501
dataset_version='hard',
),
pred_role='BOT',
)
bigcodebench_hard_instruct_datasets = [
dict(
abbr='bigcodebench_hard_instruct',
type=BigCodeBenchDataset,
path='opencompass/bigcodebench',
reader_cfg=bigcodebench_hard_reader_cfg,
infer_cfg=bigcodebench_hard_infer_cfg,
eval_cfg=bigcodebench_hard_eval_cfg,
release_version='v0.1.2',
dataset_version='hard',
)
]
with read_base():
from .bigcodebench_hard_instruct_gen import bigcodebench_hard_instruct_datasets # noqa: F401, F403

2
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_gen.py
View File

@ -1,4 +1,4 @@
from mmengine.config import read_base
with read_base():
from .bigcodebench_hard_instruct_gen_8815eb import bigcodebench_hard_instruct_datasets # noqa: F401, F403
from .bigcodebench_hard_instruct_gen_c3d5ad import bigcodebench_hard_instruct_datasets # noqa: F401, F403

5
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_gen_c3d5ad.py
View File

@ -15,8 +15,9 @@ bigcodebench_hard_infer_cfg = dict(prompt_template=dict(
round=[
dict(role='HUMAN', prompt='{instruct_prompt}'),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer)
)
bigcodebench_hard_eval_cfg = dict(
evaluator=dict(

132
opencompass/configs/datasets/cmmlu/cmmlu_gen.py
View File

@ -1,130 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import CMMLUDataset
from opencompass.utils.text_postprocessors import match_answer_pattern
from mmengine.config import read_base
cmmlu_subject_mapping = {
'agronomy': '农学',
'anatomy': '解剖学',
'ancient_chinese': '古汉语',
'arts': '艺术学',
'astronomy': '天文学',
'business_ethics': '商业伦理',
'chinese_civil_service_exam': '中国公务员考试',
'chinese_driving_rule': '中国驾驶规则',
'chinese_food_culture': '中国饮食文化',
'chinese_foreign_policy': '中国外交政策',
'chinese_history': '中国历史',
'chinese_literature': '中国文学',
'chinese_teacher_qualification': '中国教师资格',
'clinical_knowledge': '临床知识',
'college_actuarial_science': '大学精算学',
'college_education': '大学教育学',
'college_engineering_hydrology': '大学工程水文学',
'college_law': '大学法律',
'college_mathematics': '大学数学',
'college_medical_statistics': '大学医学统计',
'college_medicine': '大学医学',
'computer_science': '计算机科学',
'computer_security': '计算机安全',
'conceptual_physics': '概念物理学',
'construction_project_management': '建设工程管理',
'economics': '经济学',
'education': '教育学',
'electrical_engineering': '电气工程',
'elementary_chinese': '小学语文',
'elementary_commonsense': '小学常识',
'elementary_information_and_technology': '小学信息技术',
'elementary_mathematics': '初等数学',
'ethnology': '民族学',
'food_science': '食品科学',
'genetics': '遗传学',
'global_facts': '全球事实',
'high_school_biology': '高中生物',
'high_school_chemistry': '高中化学',
'high_school_geography': '高中地理',
'high_school_mathematics': '高中数学',
'high_school_physics': '高中物理学',
'high_school_politics': '高中政治',
'human_sexuality': '人类性行为',
'international_law': '国际法学',
'journalism': '新闻学',
'jurisprudence': '法理学',
'legal_and_moral_basis': '法律与道德基础',
'logical': '逻辑学',
'machine_learning': '机器学习',
'management': '管理学',
'marketing': '市场营销',
'marxist_theory': '马克思主义理论',
'modern_chinese': '现代汉语',
'nutrition': '营养学',
'philosophy': '哲学',
'professional_accounting': '专业会计',
'professional_law': '专业法学',
'professional_medicine': '专业医学',
'professional_psychology': '专业心理学',
'public_relations': '公共关系',
'security_study': '安全研究',
'sociology': '社会学',
'sports_science': '体育学',
'traditional_chinese_medicine': '中医中药',
'virology': '病毒学',
'world_history': '世界历史',
'world_religions': '世界宗教'
}
QUERY_TEMPLATE = """
你回答的最后一行**必须**是以下格式 '答案: $选项' (不带引号), 其中选项是ABCD之一. 请在回答之前一步步思考.
{question}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
cmmlu_all_sets = list(cmmlu_subject_mapping.keys())
cmmlu_datasets = []
for _name in cmmlu_all_sets:
_ch_name = cmmlu_subject_mapping[_name]
prompt_prefix = f'请回答以下关于{_ch_name}的单项选择题, '
cmmlu_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=prompt_prefix+QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
cmmlu_eval_cfg = dict(
evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(
type=match_answer_pattern,
# answer_pattern=r'(?i)答案\s*:\s*([A-D])'
answer_pattern=r'(?i)答案\s*:\s*[\W]*([A-D])[\W]*',
)
)
cmmlu_datasets.append(
dict(
type=CMMLUDataset,
path='opencompass/cmmlu',
name=_name,
abbr=f'cmmlu-{_name}',
reader_cfg=dict(
input_columns=['question', 'A', 'B', 'C', 'D'],
output_column='answer',
train_split='dev',
test_split='test'),
infer_cfg=cmmlu_infer_cfg,
eval_cfg=cmmlu_eval_cfg,
))
del _name, _ch_name
with read_base():
from .cmmlu_0shot_cot_gen_305931 import cmmlu_datasets # noqa: F401, F403

181
opencompass/configs/datasets/cmmlu/cmmlu_llm_judge_gen.py
View File

@ -1,179 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import CMMLUDataset
from opencompass.utils.text_postprocessors import match_answer_pattern
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from mmengine.config import read_base
cmmlu_subject_mapping = {
'agronomy': '农学',
'anatomy': '解剖学',
'ancient_chinese': '古汉语',
'arts': '艺术学',
'astronomy': '天文学',
'business_ethics': '商业伦理',
'chinese_civil_service_exam': '中国公务员考试',
'chinese_driving_rule': '中国驾驶规则',
'chinese_food_culture': '中国饮食文化',
'chinese_foreign_policy': '中国外交政策',
'chinese_history': '中国历史',
'chinese_literature': '中国文学',
'chinese_teacher_qualification': '中国教师资格',
'clinical_knowledge': '临床知识',
'college_actuarial_science': '大学精算学',
'college_education': '大学教育学',
'college_engineering_hydrology': '大学工程水文学',
'college_law': '大学法律',
'college_mathematics': '大学数学',
'college_medical_statistics': '大学医学统计',
'college_medicine': '大学医学',
'computer_science': '计算机科学',
'computer_security': '计算机安全',
'conceptual_physics': '概念物理学',
'construction_project_management': '建设工程管理',
'economics': '经济学',
'education': '教育学',
'electrical_engineering': '电气工程',
'elementary_chinese': '小学语文',
'elementary_commonsense': '小学常识',
'elementary_information_and_technology': '小学信息技术',
'elementary_mathematics': '初等数学',
'ethnology': '民族学',
'food_science': '食品科学',
'genetics': '遗传学',
'global_facts': '全球事实',
'high_school_biology': '高中生物',
'high_school_chemistry': '高中化学',
'high_school_geography': '高中地理',
'high_school_mathematics': '高中数学',
'high_school_physics': '高中物理学',
'high_school_politics': '高中政治',
'human_sexuality': '人类性行为',
'international_law': '国际法学',
'journalism': '新闻学',
'jurisprudence': '法理学',
'legal_and_moral_basis': '法律与道德基础',
'logical': '逻辑学',
'machine_learning': '机器学习',
'management': '管理学',
'marketing': '市场营销',
'marxist_theory': '马克思主义理论',
'modern_chinese': '现代汉语',
'nutrition': '营养学',
'philosophy': '哲学',
'professional_accounting': '专业会计',
'professional_law': '专业法学',
'professional_medicine': '专业医学',
'professional_psychology': '专业心理学',
'public_relations': '公共关系',
'security_study': '安全研究',
'sociology': '社会学',
'sports_science': '体育学',
'traditional_chinese_medicine': '中医中药',
'virology': '病毒学',
'world_history': '世界历史',
'world_religions': '世界宗教',
}
QUERY_TEMPLATE = """
你回答的最后一行**必须**是以下格式 '答案: $选项' (不带引号), 其中选项是ABCD之一.
{question}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n {question}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
cmmlu_all_sets = list(cmmlu_subject_mapping.keys())
cmmlu_datasets = []
for _name in cmmlu_all_sets:
_ch_name = cmmlu_subject_mapping[_name]
prompt_prefix = f'请回答以下关于{_ch_name}的单项选择题, '
cmmlu_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=prompt_prefix + QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
cmmlu_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.",
)
],
round=[
dict(role='HUMAN', prompt=GRADER_TEMPLATE),
],
),
),
dataset_cfg=dict(
type=CMMLUDataset,
path='opencompass/cmmlu',
name=_name,
reader_cfg=dict(
input_columns=['question', 'A', 'B', 'C', 'D'],
output_column='answer',
train_split='dev',
test_split='test',
),
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
cmmlu_datasets.append(
dict(
type=CMMLUDataset,
path='opencompass/cmmlu',
name=_name,
abbr=f'cmmlu-{_name}',
reader_cfg=dict(
input_columns=['question', 'A', 'B', 'C', 'D'],
output_column='answer',
train_split='dev',
test_split='test',
),
infer_cfg=cmmlu_infer_cfg,
eval_cfg=cmmlu_eval_cfg,
mode='singlescore',
)
)
del _name, _ch_name
with read_base():
from .cmmlu_llmjudge_gen_e1cd9a import cmmlu_datasets # noqa: F401, F403

32
opencompass/configs/datasets/drop/drop_gen.py
View File

@ -1,34 +1,4 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import DropOpenAIDataset, DropOpenAIEvaluator
with read_base():
from .drop_examples import drop_examples # noqa: F401, F403
drop_reader_cfg = dict(
input_columns=['prompt'],
output_column='answers',
train_split='validation',
test_split='validation',
)
template = f'You will be asked to read a passage and answer a question. Some examples of passages and Q&A are provided below.\n\n{drop_examples}\n\n# Your Task\n\n---\n{{prompt}}\n\nThink step by step, then write a line of the form "Answer: $ANSWER" at the end of your response.'
drop_infer_cfg = dict(
prompt_template=dict(type=PromptTemplate, template=dict(round=[dict(role='HUMAN', prompt=template)])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
drop_eval_cfg = dict(evaluator=dict(type=DropOpenAIEvaluator))
drop_datasets = [
dict(
abbr='drop',
type=DropOpenAIDataset,
path='data/drop_simple_eval/dev.jsonl',
reader_cfg=drop_reader_cfg,
infer_cfg=drop_infer_cfg,
eval_cfg=drop_eval_cfg)
]
from .drop_openai_simple_evals_gen_3857b0 import drop_datasets # noqa: F401, F403

84
opencompass/configs/datasets/drop/drop_llm_judge_gen.py
View File

@ -1,86 +1,4 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import DropOpenAIDataset
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
with read_base():
from .drop_examples import drop_examples # noqa: F401, F403
drop_reader_cfg = dict(
input_columns=['prompt'],
output_column='answers',
train_split='validation',
test_split='validation',
)
template = f'You will be asked to read a passage and answer a question. Some examples of passages and Q&A are provided below.\n\n{drop_examples}\n\n# Your Task\n\n---\n{{prompt}}\n\nThink step by step, then write a line of the form "Answer: $ANSWER" at the end of your response.'
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {prompt}\n \n<Original Question End>\n\n
<Gold Target Begin>: \n{answers}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
drop_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[dict(role='HUMAN', prompt=template)]),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
drop_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.",
)
],
round=[
dict(role='HUMAN', prompt=GRADER_TEMPLATE),
],
),
),
dataset_cfg=dict(
type=DropOpenAIDataset,
path='data/drop_simple_eval/dev.jsonl',
reader_cfg=drop_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
drop_datasets = [
dict(
abbr='drop',
type=DropOpenAIDataset,
path='data/drop_simple_eval/dev.jsonl',
reader_cfg=drop_reader_cfg,
infer_cfg=drop_infer_cfg,
eval_cfg=drop_eval_cfg,
)
]
from .drop_llmjudge_gen_3857b0 import drop_datasets # noqa: F401, F403

54
opencompass/configs/datasets/gpqa/gpqa_gen.py
View File

@ -1,52 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import GPQADataset, GPQA_Simple_Eval_postprocess, GPQAEvaluator
from mmengine.config import read_base
# openai_simple_eval prompt
align_prompt = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD. Think step by step before answering.
{question}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
gpqa_reader_cfg = dict(
input_columns=['question', 'A', 'B', 'C', 'D'],
output_column='answer')
gpqa_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=align_prompt),
], )),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
gpqa_eval_cfg = dict(evaluator=dict(type=GPQAEvaluator),
pred_postprocessor=dict(type=GPQA_Simple_Eval_postprocess))
gpqa_datasets = []
gpqa_subsets = {
# 'extended': 'gpqa_extended.csv',
# 'main': 'gpqa_main.csv',
'diamond': 'gpqa_diamond.csv'
}
for split in list(gpqa_subsets.keys()):
gpqa_datasets.append(
dict(
abbr='GPQA_' + split,
type=GPQADataset,
path='./data/gpqa/',
name=gpqa_subsets[split],
reader_cfg=gpqa_reader_cfg,
infer_cfg=gpqa_infer_cfg,
eval_cfg=gpqa_eval_cfg)
)
with read_base():
from .gpqa_openai_simple_evals_gen_5aeece import gpqa_datasets # noqa: F401, F403

107
opencompass/configs/datasets/gpqa/gpqa_llm_judge_gen.py
View File

@ -1,105 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import GPQADataset, GPQA_Simple_Eval_postprocess
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from mmengine.config import read_base
# openai_simple_eval prompt
align_prompt = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD.
{question}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {question}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
gpqa_reader_cfg = dict(
input_columns=['question', 'A', 'B', 'C', 'D'],
output_column='answer')
gpqa_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=align_prompt),
], )),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
gpqa_datasets = []
gpqa_subsets = {
# 'extended': 'gpqa_extended.csv',
# 'main': 'gpqa_main.csv',
'diamond': 'gpqa_diamond.csv'
}
for split in list(gpqa_subsets.keys()):
gpqa_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt=GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=GPQADataset,
path='./data/gpqa/',
name=gpqa_subsets[split],
reader_cfg=gpqa_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
gpqa_datasets.append(
dict(
abbr='GPQA_' + split,
type=GPQADataset,
path='./data/gpqa/',
name=gpqa_subsets[split],
reader_cfg=gpqa_reader_cfg,
infer_cfg=gpqa_infer_cfg,
eval_cfg=gpqa_eval_cfg,
mode='singlescore',
)
)
with read_base():
from .gpqa_0shot_nocot_genericllmeval_gen_772ea0 import gpqa_datasets # noqa: F401, F403

60
opencompass/configs/datasets/hellaswag/hellaswag_gen.py
View File

@ -1,58 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import FixKRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccwithDetailsEvaluator
from opencompass.datasets import HellaswagDatasetwithICE
from opencompass.utils.text_postprocessors import first_option_postprocess
from mmengine.config import read_base
hellaswag_reader_cfg = dict(
input_columns=['ctx', 'A', 'B', 'C', 'D'],
output_column='label',
train_split='train',
test_split='val',
)
hellaswag_infer_cfg = dict(
ice_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=f'{{ctx}}\nA) {{A}}\nB) {{B}}\nC) {{C}}\nD) {{D}}\nWhat is the right option?'),
dict(role='BOT', prompt='{label}\n'),
]
),
),
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(role='HUMAN', prompt='Continue the following text without adding any additional information or formatting:\n'),
'</E>',
],
round=[
dict(role='HUMAN', prompt=f'{{ctx}}\nA) {{A}}\nB) {{B}}\nC) {{C}}\nD) {{D}}\nWhat is the right option?'),
dict(role='BOT', prompt='{label}\n'),
],
),
ice_token='</E>',
),
retriever=dict(type=FixKRetriever, fix_id_list=list(range(10))),
inferencer=dict(type=GenInferencer),
)
hellaswag_eval_cfg = dict(
evaluator=dict(type=AccwithDetailsEvaluator),
pred_role='BOT',
pred_postprocessor=dict(type=first_option_postprocess, options='ABCD'),
)
hellaswag_datasets = [
dict(
abbr='hellaswag',
type=HellaswagDatasetwithICE,
path='opencompass/hellaswag_ice',
reader_cfg=hellaswag_reader_cfg,
infer_cfg=hellaswag_infer_cfg,
eval_cfg=hellaswag_eval_cfg,
)
]
with read_base():
from .hellaswag_10shot_gen_e42710 import hellaswag_datasets # noqa: F401, F403

96
opencompass/configs/datasets/hellaswag/hellaswag_llm_judge_gen.py
View File

@ -1,94 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccwithDetailsEvaluator
from opencompass.datasets import HellaswagDatasetwithICE
from opencompass.utils.text_postprocessors import first_option_postprocess
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from mmengine.config import read_base
hellaswag_reader_cfg = dict(
input_columns=['ctx', 'A', 'B', 'C', 'D'],
output_column='label',
train_split='train',
test_split='val',
)
align_prompt = """Continue the following text without adding any additional information or formatting:
{ctx}
A) {A}
B) {B}
C) {C}
D) {D}
What is the right option?'"""
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {ctx}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n<Original Question End>\n\n
<Gold Target Begin>: \n{label}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
hellaswag_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=align_prompt),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
hellaswag_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.",
)
],
round=[
dict(role='HUMAN', prompt=GRADER_TEMPLATE),
],
),
),
dataset_cfg=dict(
type=HellaswagDatasetwithICE,
path='opencompass/hellaswag_ice',
reader_cfg=hellaswag_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
hellaswag_datasets = [
dict(
abbr='hellaswag',
type=HellaswagDatasetwithICE,
path='opencompass/hellaswag_ice',
reader_cfg=hellaswag_reader_cfg,
infer_cfg=hellaswag_infer_cfg,
eval_cfg=hellaswag_eval_cfg,
)
]
with read_base():
from .hellaswag_llmjudge_gen_809ef1 import hellaswag_datasets # noqa: F401, F403

38
opencompass/configs/datasets/humaneval/humaneval_gen.py
View File

@ -1,36 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import HumanevalDataset, HumanEvalEvaluator, humaneval_postprocess_v2
from mmengine.config import read_base
humaneval_reader_cfg = dict(
input_columns=['prompt'], output_column='task_id', train_split='test')
# TODO: allow empty output-column
humaneval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt='Read the following function signature and docstring, and fully implement the function described. Your response should only contain the code for this function.\n{prompt}'),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
humaneval_eval_cfg = dict(
evaluator=dict(type=HumanEvalEvaluator),
pred_role='BOT',
k=[1, 10, 100], # the parameter only for humaneval
pred_postprocessor=dict(type=humaneval_postprocess_v2),
)
humaneval_datasets = [
dict(
abbr='openai_humaneval',
type=HumanevalDataset,
path='opencompass/humaneval',
reader_cfg=humaneval_reader_cfg,
infer_cfg=humaneval_infer_cfg,
eval_cfg=humaneval_eval_cfg)
]
with read_base():
from .humaneval_openai_sample_evals_gen_dcae0e import humaneval_datasets # noqa: F401, F403

62
opencompass/configs/datasets/korbench/korbench_gen.py
View File

@ -1,60 +1,4 @@
from opencompass.datasets.korbench.korbench import korbenchDataset, korbenchEvaluator
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from mmengine.config import read_base
categories = ['cipher', 'counterfactual', 'logic', 'operation', 'puzzle']
korbench_0shot_single_datasets = []
for category in categories:
# Prompt template
prompt_template = dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='HUMAN',
prompt=''
)
],
round=[
dict(
role='HUMAN',
prompt='{prompt}' # f-string
)
]
)
)
# Reader configuration
reader_cfg = dict(
input_columns=['prompt'],
output_column='answer',
)
# Inference configuration
infer_cfg = dict(
prompt_template=prompt_template,
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
# Evaluation configuration
eval_cfg = dict(
evaluator=dict(type=korbenchEvaluator),
pred_role='BOT',
)
korbench_dataset = dict(
type=korbenchDataset,
abbr=f'korbench_{category}',
path='opencompass/korbench',
prompt_mode='0_shot',
category=category,
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
korbench_0shot_single_datasets.append(korbench_dataset)
with read_base():
from .korbench_single_0_shot_gen import korbench_0shot_single_datasets # noqa: F401, F403

115
opencompass/configs/datasets/korbench/korbench_llm_judge_gen.py
View File

@ -1,113 +1,4 @@
from opencompass.datasets.korbench.korbench import korbenchDataset, korbenchEvaluator
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from mmengine.config import read_base
categories = ['cipher', 'counterfactual', 'logic', 'operation', 'puzzle']
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {question}\n {options_str} \n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
korbench_0shot_single_datasets = []
for category in categories:
# Prompt template
prompt_template = dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='HUMAN',
prompt=''
)
],
round=[
dict(
role='HUMAN',
prompt='{prompt}' # f-string
)
]
)
)
# Reader configuration
reader_cfg = dict(
input_columns=['prompt'],
output_column='answer',
)
# Inference configuration
infer_cfg = dict(
prompt_template=prompt_template,
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
# Evaluation configuration
eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt=GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=korbenchDataset,
path='opencompass/korbench',
reader_cfg=reader_cfg,
prompt_mode='0_shot',
category=category,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
korbench_dataset = dict(
type=korbenchDataset,
abbr=f'korbench_{category}',
path='opencompass/korbench',
prompt_mode='0_shot',
category=category,
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
korbench_0shot_single_datasets.append(korbench_dataset)
with read_base():
from .korbench_single_0shot_genericllmeval_gen_56cf43 import korbench_0shot_single_datasets # noqa: F401, F403

2
opencompass/configs/datasets/korbench/korbench_single_0_shot_gen.py
View File

@ -37,7 +37,7 @@ for category in categories:
infer_cfg = dict(
prompt_template=prompt_template,
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024),
inferencer=dict(type=GenInferencer),
)
# Evaluation configuration

116
opencompass/configs/datasets/korbench/korbench_single_0shot_genericllmeval_gen_56cf43.py Normal file
View File

@ -0,0 +1,116 @@
from opencompass.datasets.korbench.korbench import korbenchDataset, korbenchEvaluator
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
categories = ['cipher', 'counterfactual', 'logic', 'operation', 'puzzle']
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n{prompt}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
korbench_0shot_single_datasets = []
for category in categories:
# Prompt template
prompt_template = dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='HUMAN',
prompt=''
)
],
round=[
dict(
role='HUMAN',
prompt='{prompt}' # f-string
)
]
)
)
# Reader configuration
reader_cfg = dict(
input_columns=['prompt'],
output_column='answer',
)
# Inference configuration
infer_cfg = dict(
prompt_template=prompt_template,
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
# Evaluation configuration
eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt=GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=korbenchDataset,
path='opencompass/korbench',
prompt_mode='0_shot',
category=category,
reader_cfg=reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
# Dataset
korbench_dataset = dict(
type=korbenchDataset,
abbr=f'korbench_{category}',
path='opencompass/korbench',
prompt_mode='0_shot',
category=category,
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
mode='singlescore',
)
korbench_0shot_single_datasets.append(korbench_dataset)

166
opencompass/configs/datasets/livecodebench/livecodebench_gen.py
View File

@ -1,164 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import (
LCBCodeGenerationDataset,
LCBCodeExecutionDataset,
LCBTestOutputPredictionDataset,
LCBCodeGenerationEvaluator,
LCBCodeExecutionEvaluator,
LCBTestOutputEvaluator
)
from opencompass.datasets.livecodebench import TestOutputPromptConstants
from mmengine.config import read_base
lcb_code_generation_reader_cfg = dict(
input_columns=[
'question_content',
'format_prompt',
],
# output_column='evaluation_sample',
output_column='question_id',
)
SYSTEM_MESSAGE_GENERIC = f'You are an expert Python programmer. You will be given a question (problem specification) and will generate a correct Python program that matches the specification and passes all tests. You will NOT return anything except for the program.'
prompt_template = '### Question:\n{question_content}\n\n{format_prompt}' + \
'### Answer: (use the provided format with backticks)\n\n'
# Code Generation Tasks
lcb_code_generation_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(
role='HUMAN',
prompt=prompt_template
)
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer)
)
lcb_code_generation_eval_cfg = dict(
evaluator=dict(
type=LCBCodeGenerationEvaluator,
num_process_evaluate=4,
timeout=6,
),
pred_role='BOT',
)
LCBCodeGeneration_dataset = dict(
type=LCBCodeGenerationDataset,
abbr='lcb_code_generation',
path='opencompass/code_generation_lite',
reader_cfg=lcb_code_generation_reader_cfg,
infer_cfg=lcb_code_generation_infer_cfg,
eval_cfg=lcb_code_generation_eval_cfg
)
# Code Execution Dataset
lcb_code_execution_reader_cfg = dict(
input_columns=[
'prompt',
],
output_column='evaluation_sample',
)
lcb_code_execution_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt='You are an expert at Python programming, code execution, test case generation, and fuzzing.'
),
],
round=[
dict(
role='HUMAN',
prompt='{prompt}'
)
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer)
)
lcb_code_execution_eval_cfg = dict(
evaluator=dict(
type=LCBCodeExecutionEvaluator,
),
pred_role='BOT',
)
LCBCodeExecution_dataset = dict(
type=LCBCodeExecutionDataset,
abbr='lcb_code_execution',
path='opencompass/execution-v2',
reader_cfg=lcb_code_execution_reader_cfg,
infer_cfg=lcb_code_execution_infer_cfg,
eval_cfg=lcb_code_execution_eval_cfg,
)
# TestOuputput Dataset
lcb_test_output_reader_cfg = dict(
input_columns=[
'prompt',
],
output_column='evaluation_sample',
)
system_prompt = 'You are an expert Python programmer. You will be given a question (problem specification) and will generate a correct Python program that matches the specification and passes all tests. You will NOT return anything except for the program.'
lcb_test_output_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
# begin=[
# dict(
# role='SYSTEM',
# prompt=system_prompt
# ),
# ],
round=[
dict(
role='HUMAN',
prompt='{prompt}'
)
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer)
)
lcb_test_output_eval_cfg = dict(
evaluator=dict(
type=LCBTestOutputEvaluator,
),
pred_role='BOT',
)
LCBTestOutput_dataset = dict(
type=LCBTestOutputPredictionDataset,
abbr='lcb_test_output',
path='opencompass/test_generation',
reader_cfg=lcb_test_output_reader_cfg,
infer_cfg=lcb_test_output_infer_cfg,
eval_cfg=lcb_test_output_eval_cfg,
)
LCB_datasets = [
LCBCodeGeneration_dataset,
LCBCodeExecution_dataset,
LCBTestOutput_dataset,
]
with read_base():
from .livecodebench_gen_a4f90b import LCB_datasets # noqa: F401, F403

96
opencompass/configs/datasets/math/math_prm800k_500_0shot_nocot_genericllmeval_gen_6ff468.py Normal file
View File

@ -0,0 +1,96 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from opencompass.datasets import MATHDataset
# ----------------------------- Detailed Config -----------------------------
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{problem}\nRemember to put your final answer within \\boxed{}.'),
]
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n{problem}\n<Original Question End>\n\n
<Gold Target Begin>: \n{solution}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
# Evaluation configuration
math_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=MATHDataset,
path='opencompass/math',
file_name = 'test_prm800k_500.json',
reader_cfg=math_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
math_datasets = [
dict(
type=MATHDataset,
abbr='math_prm800k_500-llmjudge',
path='opencompass/math',
file_name = 'test_prm800k_500.json',
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg,
mode='singlescore',
)
]

47
opencompass/configs/datasets/math/math_prm800k_500_gen.py
View File

@ -1,45 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import (
MATHDataset,
MATHEvaluator,
math_postprocess_v2,
normalize_final_answer,
)
from mmengine.config import read_base
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(
role='HUMAN',
prompt='{problem}\nPlease reason step by step, and put your final answer within \\boxed{}.',
),
]
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
# postprocess v2
math_eval_cfg = dict(
evaluator=dict(type=MATHEvaluator, version='v2'),
pred_postprocessor=dict(type=math_postprocess_v2),
)
math_datasets = [
dict(
type=MATHDataset,
abbr='math_prm800k_500',
path='opencompass/math',
file_name='test_prm800k_500.json',
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg,
)
]
with read_base():
from .math_prm800k_500_0shot_cot_gen import math_datasets # noqa: F401, F403

93
opencompass/configs/datasets/math/math_prm800k_500_llm_judge_gen.py
View File

@ -1,91 +1,4 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from opencompass.datasets import MATHDataset
from mmengine.config import read_base
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{problem}\nRemember to put your final answer within \\boxed{}.'),
]
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n{problem}\n<Original Question End>\n\n
<Gold Target Begin>: \n{solution}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
# Evaluation configuration
math_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt=GRADER_TEMPLATE
),
]),
),
dataset_cfg=dict(
type=MATHDataset,
path='opencompass/math',
file_name='test_prm800k_500.json',
reader_cfg=math_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
math_datasets = [
dict(
type=MATHDataset,
abbr='math_prm800k_500-llmjudge',
path='opencompass/math',
file_name='test_prm800k_500.json',
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg,
mode='singlescore',
)
]
with read_base():
from .math_prm800k_500_0shot_nocot_genericllmeval_gen_6ff468 import math_datasets # noqa: F401, F403

57
opencompass/configs/datasets/mmlu/mmlu_gen.py
View File

@ -1,59 +1,4 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import MMLUDataset
from opencompass.utils.text_postprocessors import match_answer_pattern
with read_base():
from .mmlu_all_sets import mmlu_all_sets
# None of the mmlu dataset in huggingface is correctly parsed, so we use our own dataset reader
# Please download the dataset from https://people.eecs.berkeley.edu/~hendrycks/data.tar
QUERY_TEMPLATE = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD. Think step by step before answering.
{input}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
mmlu_reader_cfg = dict(
input_columns=['input', 'A', 'B', 'C', 'D'],
output_column='target',
train_split='dev')
mmlu_datasets = []
for name in mmlu_all_sets:
mmlu_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
mmlu_eval_cfg = dict(
evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(type=match_answer_pattern, answer_pattern=r'(?i)ANSWER\s*:\s*([A-D])'))
mmlu_datasets.append(
dict(
abbr=f'lukaemon_mmlu_{name}',
type=MMLUDataset,
path='opencompass/mmlu',
name=name,
reader_cfg=mmlu_reader_cfg,
infer_cfg=mmlu_infer_cfg,
eval_cfg=mmlu_eval_cfg,
))
from .mmlu_openai_simple_evals_gen_b618ea import mmlu_datasets # noqa: F401, F403

104
opencompass/configs/datasets/mmlu/mmlu_llm_judge_gen.py
View File

@ -1,106 +1,4 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import MMLUDataset
from opencompass.utils.text_postprocessors import match_answer_pattern
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
with read_base():
from .mmlu_all_sets import mmlu_all_sets
# None of the mmlu dataset in huggingface is correctly parsed, so we use our own dataset reader
# Please download the dataset from https://people.eecs.berkeley.edu/~hendrycks/data.tar
QUERY_TEMPLATE = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD.
{input}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {input}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n<Original Question End>\n\n
<Gold Target Begin>: \n{target}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
mmlu_reader_cfg = dict(
input_columns=['input', 'A', 'B', 'C', 'D'],
output_column='target',
train_split='dev',
)
mmlu_datasets = []
for name in mmlu_all_sets:
mmlu_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
mmlu_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.",
)
],
round=[
dict(role='HUMAN', prompt=GRADER_TEMPLATE),
],
),
),
dataset_cfg=dict(
type=MMLUDataset,
path='opencompass/mmlu',
name=name,
reader_cfg=mmlu_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
mmlu_datasets.append(
dict(
abbr=f'lukaemon_mmlu_{name}',
type=MMLUDataset,
path='opencompass/mmlu',
name=name,
reader_cfg=mmlu_reader_cfg,
infer_cfg=mmlu_infer_cfg,
eval_cfg=mmlu_eval_cfg,
mode='singlescore',
)
)
from .mmlu_llmjudge_gen_f4336b import mmlu_datasets # noqa: F401, F403

62
opencompass/configs/datasets/mmlu_pro/mmlu_pro_gen.py
View File

@ -1,64 +1,4 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import MMLUProDataset
from opencompass.utils.text_postprocessors import match_answer_pattern
with read_base():
from .mmlu_pro_categories import categories
QUERY_TEMPLATE = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of Options(e.g. one of ABCDEFGHIJKLMNOP). Think step by step before answering.
Question:\n
{question}
Options:\n
{options_str}
""".strip()
mmlu_pro_datasets = []
for category in categories:
mmlu_pro_reader_cfg = dict(
input_columns=['question', 'cot_content', 'options_str'],
output_column='answer',
train_split='validation',
test_split='test',
)
mmlu_pro_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN',
prompt=QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
mmlu_pro_eval_cfg = dict(
evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(
type=match_answer_pattern,
answer_pattern=r'(?i)ANSWER\s*:\s*([A-P])')
)
mmlu_pro_datasets.append(
dict(
abbr=f'mmlu_pro_{category.replace(" ", "_")}',
type=MMLUProDataset,
path='opencompass/mmlu_pro',
category=category,
reader_cfg=mmlu_pro_reader_cfg,
infer_cfg=mmlu_pro_infer_cfg,
eval_cfg=mmlu_pro_eval_cfg,
))
from .mmlu_pro_0shot_cot_gen_08c1de import mmlu_pro_datasets # noqa: F401, F403

97
opencompass/configs/datasets/mmlu_pro/mmlu_pro_llm_judge_gen.py
View File

@ -1,99 +1,4 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import MMLUProDataset, generic_llmjudge_postprocess
with read_base():
from .mmlu_pro_categories import categories
QUERY_TEMPLATE = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of Options(e.g. one of ABCDEFGHIJKLMNOP). Think step by step before answering.
Question:\n
{question}
Options:\n
{options_str}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {question}\n {options_str} \n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
mmlu_pro_datasets = []
for category in categories:
mmlu_pro_reader_cfg = dict(
input_columns=['question', 'cot_content', 'options_str'],
output_column='answer',
train_split='validation',
test_split='test',
)
mmlu_pro_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
mmlu_pro_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.",
)
],
round=[
dict(role='HUMAN', prompt=GRADER_TEMPLATE),
],
),
),
dataset_cfg=dict(
type=MMLUProDataset,
path='opencompass/mmlu_pro',
category=category,
reader_cfg=mmlu_pro_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
mmlu_pro_datasets.append(
dict(
abbr=f'mmlu_pro_{category.replace(" ", "_")}',
type=MMLUProDataset,
path='opencompass/mmlu_pro',
category=category,
reader_cfg=mmlu_pro_reader_cfg,
infer_cfg=mmlu_pro_infer_cfg,
eval_cfg=mmlu_pro_eval_cfg,
)
)
from .mmlu_pro_llm_judge_gen_6f107c import mmlu_pro_datasets # noqa: F401, F403

99
opencompass/configs/datasets/mmlu_pro/mmlu_pro_llm_judge_gen_6f107c.py Normal file
View File

@ -0,0 +1,99 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import MMLUProDataset, generic_llmjudge_postprocess
with read_base():
from .mmlu_pro_categories import categories
QUERY_TEMPLATE = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of Options(e.g. one of ABCDEFGHIJKLMNOP). Think step by step before answering.
Question:\n
{question}
Options:\n
{options_str}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {question}\n {options_str} \n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
mmlu_pro_datasets = []
for category in categories:
mmlu_pro_reader_cfg = dict(
input_columns=['question', 'cot_content', 'options_str'],
output_column='answer',
train_split='validation',
test_split='test',
)
mmlu_pro_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
mmlu_pro_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.",
)
],
round=[
dict(role='HUMAN', prompt=GRADER_TEMPLATE),
],
),
),
dataset_cfg=dict(
type=MMLUProDataset,
path='opencompass/mmlu_pro',
category=category,
reader_cfg=mmlu_pro_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
mmlu_pro_datasets.append(
dict(
abbr=f'mmlu_pro_{category.replace(" ", "_")}',
type=MMLUProDataset,
path='opencompass/mmlu_pro',
category=category,
reader_cfg=mmlu_pro_reader_cfg,
infer_cfg=mmlu_pro_infer_cfg,
eval_cfg=mmlu_pro_eval_cfg,
)
)