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

resolve new conflicts

Browse Source
This commit is contained in:
marcry 2025-05-09 05:59:40 +00:00
commit f7ae6c690e
28 changed files with 1044 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
dataset-index.yml
View File

@ -128,6 +128,24 @@
paper: https://arxiv.org/abs/2501.18362
configpath: opencompass/configs/datasets/MedXpertQA/MedXpertQA_gen.py
configpath_llmjudge: opencompass/configs/datasets/MedXpertQA/MedXpertQA_llmjudge_gen.py
- ClinicBench:
name: ClinicBench
category: Knowledge / Medicine
paper: https://arxiv.org/abs/2405.00716
configpath: ''
configpath_llmjudge: opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen.py
- ScienceQA:
name: ScienceQA
category: Knowledge / Medicine
paper: https://arxiv.org/abs/2209.09513
configpath: ''
configpath_llmjudge: opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen.py
- PubMedQA:
name: PubMedQA
category: Knowledge / Medicine
paper: https://arxiv.org/abs/1909.06146
configpath: ''
configpath_llmjudge: opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen.py
- musr:
name: MuSR
category: Reasoning
@ -343,6 +361,12 @@
paper: https://arxiv.org/pdf/2004.05986
configpath: opencompass/configs/datasets/CLUE_C3/CLUE_C3_gen.py
configpath_llmjudge: ''
- CARDBiomedBench:
name: CARDBiomedBench
category: Knowledge / Medicine
paper: https://www.biorxiv.org/content/10.1101/2025.01.15.633272v1
configpath: opencompass/configs/datasets/CARDBiomedBench
configpath_llmjudge: 'opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen_99a231.py'
- cb:
name: SuperGLUE / CB
category: Reasoning
@ -1029,6 +1053,12 @@
paper: ''
configpath: opencompass/configs/datasets/internsandbox/internsandbox_gen_44b982.py
configpath_llmjudge: ''
- nejmaibench:
name: nejmaibench
category: Science /Medicine
paper: https://arxiv.org/pdf/2308.04709
configpath: opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen.py
configpath_llmjudge: opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen.py
- medbullets:
name: Medbullets
category: Science /Medicine

101
opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen_99a231.py Normal file
View File

@ -0,0 +1,101 @@
from opencompass.datasets import CARDBiomedBenchDataset
from opencompass.datasets import generic_llmjudge_postprocess
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
ZERO_SHOT_PROMPT = 'You are an expert in {expert}.\n{question}\n'
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>: Q: You are an expert in {expert}.\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()
# Reader configuration
reader_cfg = dict(
input_columns=[
'question',
'answer',
'Bio_Category',
'SQL_Category',
'uuid',
'template uuid',
'expert',
],
output_column='answer',
)
# Inference configuration
infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(
role='HUMAN',
prompt=ZERO_SHOT_PROMPT, # prompt mode: zero-shot
),
],
),
),
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=CARDBiomedBenchDataset,
path='NIH-CARD/CARDBiomedBench',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
cardbiomedbench_dataset = dict(
type=CARDBiomedBenchDataset,
abbr='cardbiomedbench',
path='NIH-CARD/CARDBiomedBench',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
cardbiomedbench_datasets = [cardbiomedbench_dataset]

4
opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .ClinicBench_llmjudge_gen_d09668 import ClinicBench_datasets

100
opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen_d09668.py Normal file
View File

@ -0,0 +1,100 @@
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 generic_llmjudge_postprocess
from opencompass.datasets.ClinicBench import ClinicBenchDataset
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
{choices}
""".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 {choices} \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()
ClinicBench_datasets = []
ClinicBench_reader_cfg = dict(
input_columns=['question', 'choices'],
output_column='label',
)
ClinicBench_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),
)
ClinicBench_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=ClinicBenchDataset,
path='xuxuxuxuxu/Pharmacology-QA',
reader_cfg=ClinicBench_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
ClinicBench_datasets.append(
dict(
abbr=f'ClinicBench',
type=ClinicBenchDataset,
path='xuxuxuxuxu/Pharmacology-QA',
reader_cfg=ClinicBench_reader_cfg,
infer_cfg=ClinicBench_infer_cfg,
eval_cfg=ClinicBench_eval_cfg,
)
)

4
opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .PubMedQA_llmjudge_gen_f00302 import PubMedQA_datasets

94
opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen_f00302.py Normal file
View File

@ -0,0 +1,94 @@
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 generic_llmjudge_postprocess
from opencompass.datasets.PubMedQA import PubMedQADataset
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
{choices}
""".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 {choices} \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()
PubMedQA_datasets = []
PubMedQA_reader_cfg = dict(
input_columns=['question', 'choices'],
output_column='label',
)
PubMedQA_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),
)
PubMedQA_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=PubMedQADataset,
path='qiaojin/PubMedQA',
reader_cfg=PubMedQA_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
PubMedQA_datasets.append(
dict(
abbr=f'PubMedQA',
type=PubMedQADataset,
path='qiaojin/PubMedQA',
reader_cfg=PubMedQA_reader_cfg,
infer_cfg=PubMedQA_infer_cfg,
eval_cfg=PubMedQA_eval_cfg,
)
)

4
opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .ScienceQA_llmjudge_gen_f00302 import ScienceQA_datasets

94
opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen_f00302.py Normal file
View File

@ -0,0 +1,94 @@
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 generic_llmjudge_postprocess
from opencompass.datasets.ScienceQA import ScienceQADataset
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
{choices}
""".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 {choices} \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()
ScienceQA_datasets = []
ScienceQA_reader_cfg = dict(
input_columns=['question', 'choices'],
output_column='label',
)
ScienceQA_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),
)
ScienceQA_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=ScienceQADataset,
path='derek-thomas/ScienceQA',
reader_cfg=ScienceQA_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
ScienceQA_datasets.append(
dict(
abbr=f'ScienceQA',
type=ScienceQADataset,
path='derek-thomas/ScienceQA',
reader_cfg=ScienceQA_reader_cfg,
infer_cfg=ScienceQA_infer_cfg,
eval_cfg=ScienceQA_eval_cfg,
)
)

4
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .nejmaibench_gen_60c8f5 import nejmaibench_datasets # noqa: F401, F403

59
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen_60c8f5.py Normal file
View File

@ -0,0 +1,59 @@
from opencompass.datasets import NejmaibenchDataset, NejmaibenchEvaluator
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
import os
SYSTEM_PROMPT = 'You are a helpful medical assistant.\n\n' # Where to put this?
ZERO_SHOT_PROMPT = 'Q: {question}\n Please select the correct answer from the options above and output only the corresponding letter (A, B, C, D, or E) without any explanation or additional text.\n'
# Reader configuration
reader_cfg = dict(
input_columns=[
'question',
'options',
'Subject',
'prompt_mode',
],
output_column='label',
)
# Inference configuration
infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(role='SYSTEM', fallback_role='HUMAN', prompt=SYSTEM_PROMPT),
],
round=[
dict(
role='HUMAN',
prompt=ZERO_SHOT_PROMPT, # prompt mode: zero-shot
),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
# Evaluation configuration
eval_cfg = dict(
evaluator=dict(type=NejmaibenchEvaluator),
pred_role='BOT',
)
nejmaibench_dataset = dict(
type=NejmaibenchDataset,
abbr='nejmaibench',
path='opencompass/nejmaibench',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
nejmaibench_datasets = [nejmaibench_dataset]

4
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .nejmaibench_llmjudge_gen_60c8f5 import nejmaibench_datasets # noqa: F401, F403

108
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen_60c8f5.py Normal file
View File

@ -0,0 +1,108 @@
from opencompass.datasets import NejmaibenchDataset
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.datasets import generic_llmjudge_postprocess
from opencompass.evaluator import GenericLLMEvaluator
import os
SYSTEM_PROMPT = 'You are a helpful medical assistant.\n\n' # Where to put this?
ZERO_SHOT_PROMPT = 'Q: {question}\n Please select the correct answer from the options above and output only the corresponding letter (A, B, C, D, or E) without any explanation or additional text.\n'
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>: Q: {question}\nPlease select the correct answer from the options above and output only the corresponding letter (A, B, C, D, or E) without any explanation or additional text.\n\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()
# Reader configuration
reader_cfg = dict(
input_columns=[
'question',
'options',
'Subject',
'prompt_mode',
],
output_column='label',
)
# Inference configuration
infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(role='SYSTEM', fallback_role='HUMAN', prompt=SYSTEM_PROMPT),
],
round=[
dict(
role='HUMAN',
prompt=ZERO_SHOT_PROMPT, # prompt mode: zero-shot
),
],
),
),
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=NejmaibenchDataset,
path='opencompass/nejmaibench',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
)
nejmaibench_dataset = dict(
type=NejmaibenchDataset,
abbr='nejmaibench',
path='opencompass/nejmaibench',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
nejmaibench_datasets = [nejmaibench_dataset]

16
opencompass/configs/models/gemma/vllm_gemma_3_12b_it.py Normal file
View File

@ -0,0 +1,16 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='gemma-3-12b-it-vllm',
path='google/gemma-3-12b-it',
model_kwargs=dict(tensor_parallel_size=4,
# for long context
rope_scaling={'factor': 8.0, 'rope_type': 'linear'}),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]

16
opencompass/configs/models/gemma/vllm_gemma_3_27b_it.py Normal file
View File

@ -0,0 +1,16 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='gemma-3-27b-it-vllm',
path='google/gemma-3-27b-it',
model_kwargs=dict(tensor_parallel_size=4,
# for long context
rope_scaling={'factor': 8.0, 'rope_type': 'linear'}),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]

17
opencompass/configs/models/gemma/vllm_gemma_3_4b_it.py Normal file
View File

@ -0,0 +1,17 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='gemma-3-4b-it-vllm',
path='google/gemma-3-4b-it',
model_kwargs=dict(tensor_parallel_size=2,
# for long context
rope_scaling={'factor': 8.0, 'rope_type': 'linear'}),
max_seq_len=140000,
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=2),
)
]

19
opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct_128k.py Normal file
View File

@ -0,0 +1,19 @@
from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='internlm3-8b-instruct-turbomind',
path='internlm/internlm3-8b-instruct',
engine_config=dict(session_len=142000, max_batch_size=1, tp=2,
# for long context
rope_scaling_factor=6.0),
gen_config=dict(
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=8192
),
max_seq_len=142000,
max_out_len=8192,
batch_size=1,
run_cfg=dict(num_gpus=2),
)
]

20
opencompass/configs/models/hf_internlm/lmdeploy_oreal_32b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='OREAL-32B',
path='internlm/OREAL-32B',
engine_config=dict(session_len=32768, max_batch_size=16, tp=4),
gen_config=dict(top_k=1,
temperature=1e-6,
top_p=0.9,
max_new_tokens=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=16,
run_cfg=dict(num_gpus=4),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2.5-14b-instruct-vllm',
path='Qwen/Qwen2.5-14B-Instruct',
model_kwargs=dict(
tensor_parallel_size=4,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2.5-32b-instruct-vllm',
path='Qwen/Qwen2.5-32B-Instruct',
model_kwargs=dict(
tensor_parallel_size=8,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=8),
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2_5-72b-instruct-vllm',
path='Qwen/Qwen2.5-72B-Instruct',
model_kwargs=dict(
tensor_parallel_size=8,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=8),
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2.5-7b-instruct-vllm',
path='Qwen/Qwen2.5-7B-Instruct',
model_kwargs=dict(
tensor_parallel_size=4,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]

30
opencompass/datasets/CARDBiomedBench.py Normal file
View File

@ -0,0 +1,30 @@
from datasets import load_dataset
from opencompass.registry import LOAD_DATASET
from .base import BaseDataset
def _parse(item, prompt_mode):
item['expert'] = item['Bio_Category']
item['start'] = chr(65)
item['end'] = chr(65 + len(item.get('choices', {'label': []})['label']) -
1)
item['prompt_mode'] = prompt_mode
return item
@LOAD_DATASET.register_module()
class CARDBiomedBenchDataset(BaseDataset):
@staticmethod
def load(path: str, prompt_mode: str, **kwargs):
data_files = {'test': 'data/CARDBiomedBench.csv'}
dataset = load_dataset(path, data_files=data_files, split='test')
# dataset = dataset.select(range(200))
if prompt_mode == 'zero-shot':
dataset = dataset.map(lambda item: _parse(item, prompt_mode),
load_from_cache_file=False)
elif prompt_mode == 'few-shot':
pass # TODO: Implement few-shot prompt
return dataset

19
opencompass/datasets/ClinicBench.py Normal file
View File

@ -0,0 +1,19 @@
from datasets import load_dataset
from opencompass.registry import LOAD_DATASET
from .base import BaseDataset
@LOAD_DATASET.register_module()
class ClinicBenchDataset(BaseDataset):
@staticmethod
def load_single(path):
dataset = load_dataset(path)['train']
return dataset
@staticmethod
def load(path):
dataset = ClinicBenchDataset.load_single(path)
return dataset

34
opencompass/datasets/PubMedQA.py Normal file
View File

@ -0,0 +1,34 @@
from datasets import Dataset, load_dataset
from opencompass.registry import LOAD_DATASET
from .base import BaseDataset
@LOAD_DATASET.register_module()
class PubMedQADataset(BaseDataset):
@staticmethod
def load_single(path):
dataset = []
ds = load_dataset(path, 'pqa_labeled')
for data in ds['train']:
data['question'] = (f"CONTEXTS: {data['context']}\n"
f"QUESTION: {data['question']}")
choices = 'A. yes\nB. no\nC. maybe'
data['choices'] = choices
if data['final_decision'] == 'yes':
data['label'] = 'A. yes'
elif data['final_decision'] == 'no':
data['label'] = 'B. no'
else:
data['label'] = 'C. maybe'
dataset.append(data)
return Dataset.from_list(dataset)
@staticmethod
def load(path):
dataset = PubMedQADataset.load_single(path)
return dataset

32
opencompass/datasets/ScienceQA.py Normal file
View File

@ -0,0 +1,32 @@
from datasets import Dataset, load_dataset
from opencompass.registry import LOAD_DATASET
from .base import BaseDataset
@LOAD_DATASET.register_module()
class ScienceQADataset(BaseDataset):
@staticmethod
def load_single(path):
dataset = []
ds = load_dataset(path)
for data in ds['test']:
if data['image'] is None:
data['label'] = chr(65 + data['answer']
) + '. ' + data['choices'][data['answer']]
choices = ''
for i in range(len(data['choices'])):
choices += chr(65 + i) + '. ' + data['choices'][i] + '\n'
data['choices'] = choices
# print(data)
dataset.append(data)
return Dataset.from_list(dataset)
@staticmethod
def load(path):
dataset = ScienceQADataset.load_single(path)
return dataset

2
opencompass/datasets/__init__.py
View File

@ -16,6 +16,7 @@ from .boolq import * # noqa: F401, F403
from .bustum import * # noqa: F401, F403
from .c3 import * # noqa: F401, F403
from .calm import * # noqa: F401, F403
from .CARDBiomedBench import CARDBiomedBenchDataset # noqa: F401
from .cb import * # noqa: F401, F403
from .ceval import * # noqa: F401, F403
from .charm import * # noqa: F401, F403
@ -111,6 +112,7 @@ from .musr import * # noqa: F401, F403
from .narrativeqa import * # noqa: F401, F403
from .natural_question import * # noqa: F401, F403
from .natural_question_cn import * # noqa: F401, F403
from .nejmaibench import * # noqa: F401, F403
from .NPHardEval import * # noqa: F401, F403
from .obqa import * # noqa: F401, F403
from .olymmath import * # noqa: F401, F403

139
opencompass/datasets/nejmaibench.py Normal file
View File

@ -0,0 +1,139 @@
import re
import pandas as pd
from datasets import Dataset
from opencompass.openicl import BaseEvaluator
from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
from opencompass.utils import get_data_path
from .base import BaseDataset
def _parse(item, prompt_mode):
# 1. 从 Choices 字符串里按行拆分出每个选项
raw_choices = item.get('Choices', '')
# 去掉首尾空白并按行分割，过滤掉空行
lines = [
line.strip() for line in raw_choices.strip().splitlines()
if line.strip()
]
# 2. 用正则去掉行首的 "A. "/"B. " 等前缀，只保留选项内容
options_list = [re.sub(r'^[A-Z]\.\s*', '', line) for line in lines]
# 3. 写回 item
item['options'] = options_list
# 4. 重建带标号的选项字符串
options_str = '\n'.join(f'{chr(65 + i)}. {opt}'
for i, opt in enumerate(options_list))
# 5. 构造 question、label、prompt_mode、start、end
item['question'] = f"{item['Question']}\n{options_str}"
item['label'] = item['Answer']
item['prompt_mode'] = prompt_mode
item['start'] = chr(65)
item['end'] = chr(65 + len(options_list) - 1)
return item
@LOAD_DATASET.register_module()
class NejmaibenchDataset(BaseDataset):
@staticmethod
def load(path: str, prompt_mode: str = 'zero-shot', **kwargs):
# 读取 CSV 文件为 DataFrame，并将 NaN 转为空字符串
path = get_data_path(path)
df = pd.read_csv(path, encoding='utf-8')
df = df.fillna('')
# 转换为字典列表
data_list = df.to_dict(orient='records')
# 将数据列表包装为 Dataset
dataset = Dataset.from_list(data_list)
# 根据提示模式进行解析
if prompt_mode == 'zero-shot':
dataset = dataset.map(lambda item: _parse(item, prompt_mode))
elif prompt_mode == 'few-shot':
pass # TODO: Implement few-shot prompt handling
return dataset
class NejmaibenchEvaluator(BaseEvaluator):
def score(self, predictions, references, test_set):
method = test_set['prompt_mode'][0]
if len(predictions) != len(references):
return {'error': 'preds and refrs have different length'}
correct = 0
count = 0
details = []
for idx, (i, j) in enumerate(zip(predictions, references)):
i = answer_cleansing(method, i, test_set['options'][idx],
test_set['label'][idx])
detail = {
'pred': i,
'answer': j,
'correct': False,
'Subject': test_set['Subject'][idx],
}
count += 1
if i == j:
correct += 1
detail['correct'] = True
details.append(detail)
result = {'accuracy': 100 * correct / count, 'details': details}
return result
@TEXT_POSTPROCESSORS.register_module()
def answer_cleansing(
method: str,
prediction: str,
options: list,
label: str,
) -> str:
# Clean up unwanted phrases in the prediction
for unwanted_phrase in [
'I understand',
'A through J',
'A through E',
'A through D',
]:
prediction = prediction.replace(unwanted_phrase, '')
options_num = len(options)
options = [chr(65 + i) for i in range(options_num)]
options_str = r'\b(' + '|'.join(options) + r')\b'
prediction = re.findall(options_str, prediction)
if len(prediction) == 0:
prediction = []
return prediction
else:
# If there is a "label" and its length is 1,
# process prediction accordingly
if len(label) == 1:
if method == 'few-shot':
answer_flag = True if len(prediction) > 1 else False
# choose the first or last element based on the answer_flag
if answer_flag:
prediction = [prediction[0]]
else:
prediction = [prediction[-1]]
elif method == 'zero-shot':
# choose the first element in list
prediction = [prediction[0]]
else:
raise ValueError('Method is not properly defined ...')
# Remove trailing period if it exists
if prediction[0] and prediction[0].endswith('.'):
prediction[0] = prediction[0][:-1]
return prediction[0]

10
opencompass/utils/datasets_info.py
View File

@ -446,6 +446,11 @@ DATASETS_MAPPING = {
"hf_id": "",
"local": "./data/ChemBench4K",
},
"opencompass/nejmaibench": {
"ms_id": "",
"hf_id": "",
"local": "./data/nejmaibench/NEJM_All_Questions_And_Answers.csv",
},
"opencompass/medbullets": {
"ms_id": "",
"hf_id": "",
@ -803,6 +808,11 @@ DATASETS_URL = {
"url":
"http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/ChemBench4K.zip",
"md5": "fc23fd21b2566a5dbbebfa4601d7779c"
},
"nejmaibench": {
"url":
"http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/nejmaibench.zip",
"md5": "e6082cae3596b3ebea73e23ba445b99e"
}
}