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

[Dataset] Support MedMCQA and MedBullets benchmark (#2054)

Browse Source 
* support medmcqa and medbullets benchmark

* Add Medbullets data folder for benchmark support

* revise gen name

* revise config file & remove csv file & add dataset info to dataset-index.yml

* remove csv file

* remove print in medbullets.py

* revise class name

* update_oss_info

---------

Co-authored-by: MaiziXiao <xxllcc1993@gmail.com>
This commit is contained in:
Wei Li 2025-05-13 17:10:50 +08:00 committed by GitHub
parent d60f59dcab
commit b84518c656
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
13 changed files with 858 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
dataset-index.yml
View File

@ -1095,3 +1095,15 @@
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
paper: https://arxiv.org/pdf/2402.18060
configpath: opencompass/configs/datasets/Medbullets/medbullets_gen.py
configpath_llmjudge: opencompass/configs/datasets/Medbullets/medbullets_llmjudge_gen.py
- medmcqa:
name: medmcqa
category: Science /Medicine
paper: https://arxiv.org/pdf/2203.14371
configpath: opencompass/configs/datasets/medmcqa/medmcqa_gen.py
configpath_llmjudge: opencompass/configs/datasets/medmcqa/medmcqa_llmjudge_gen.py

4
opencompass/configs/datasets/Medbullets/medbullets_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .medbullets_gen_60c8f5 import medbullets_datasets # noqa: F401, F403

59
opencompass/configs/datasets/Medbullets/medbullets_gen_60c8f5.py Normal file
View File

@ -0,0 +1,59 @@
from opencompass.datasets import MedbulletsDataset, MedbulletsEvaluator
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',
'question_type',
'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=MedbulletsEvaluator),
pred_role='BOT',
)
medbullets_dataset = dict(
type=MedbulletsDataset,
abbr='medbullets',
path='opencompass/medbullets',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
medbullets_datasets = [medbullets_dataset]

4
opencompass/configs/datasets/Medbullets/medbullets_llmjudge_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .medbullets_llmjudge_gen_60c8f5 import medbullets_datasets # noqa: F401, F403

106
opencompass/configs/datasets/Medbullets/medbullets_llmjudge_gen_60c8f5.py Normal file
View File

@ -0,0 +1,106 @@
from opencompass.datasets import MedbulletsDataset, medbullets_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
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',
'question_type',
'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=MedbulletsDataset,
path='opencompass/medbullets',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=medbullets_llmjudge_postprocess),
),
)
medbullets_dataset = dict(
type=MedbulletsDataset,
abbr='medbullets',
path='opencompass/medbullets',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
medbullets_datasets = [medbullets_dataset]

4
opencompass/configs/datasets/medmcqa/medmcqa_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .medmcqa_gen_60c8f5 import medmcqa_datasets # noqa: F401, F403

58
opencompass/configs/datasets/medmcqa/medmcqa_gen_60c8f5.py Normal file
View File

@ -0,0 +1,58 @@
from opencompass.datasets import MedmcqaDataset, MedmcqaEvaluator
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
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_name',
'choice_type',
'prompt_mode',
'topic_name',
],
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=MedmcqaEvaluator),
pred_role='BOT',
)
medmcqa_dataset = dict(
type=MedmcqaDataset,
abbr='medmcqa',
path='openlifescienceai/medmcqa',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
medmcqa_datasets = [medmcqa_dataset]

4
opencompass/configs/datasets/medmcqa/medmcqa_llmjudge_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .medmcqa_llmjudge_gen_60c8f5 import medmcqa_datasets # noqa: F401, F403

105
opencompass/configs/datasets/medmcqa/medmcqa_llmjudge_gen_60c8f5.py Normal file
View File

@ -0,0 +1,105 @@
from opencompass.datasets import MedmcqaDataset, medmcqa_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
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_name',
'choice_type',
'prompt_mode',
'topic_name',
],
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=MedmcqaDataset,
path='openlifescienceai/medmcqa',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=medmcqa_llmjudge_postprocess),
),
)
medmcqa_dataset = dict(
type=MedmcqaDataset,
abbr='medmcqa',
path='openlifescienceai/medmcqa',
prompt_mode='zero-shot',
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
)
medmcqa_datasets = [medmcqa_dataset]

243
opencompass/datasets/Medbullets.py Normal file
View File

@ -0,0 +1,243 @@
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, get_logger
from .base import BaseDataset
def _parse(item: dict, prompt_mode: str) -> dict:
# 构建选项列表，忽略空字符串的 ope
options_keys = ['opa', 'opb', 'opc', 'opd']
if item.get('ope', '') != '':
options_keys.append('ope')
options_list = [item.get(k, '') for k in options_keys]
item['options'] = options_list
# 构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)])
# 将选项附加到问题末尾
item['question'] = f"{item.get('question', '')}\n{options_str}"
# 标签及其他字段
item['label'] = item.get('answer_idx')
item['prompt_mode'] = prompt_mode
item['start'] = chr(65)
item['end'] = chr(65 + len(options_list) - 1)
return item
@LOAD_DATASET.register_module()
class MedbulletsDataset(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 MedbulletsEvaluator(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,
'question_type': test_set['question_type'][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]
def _generic_llmjudge_postprocess(judgement: str):
match = re.search(r'(A|B)', judgement)
grade_letter = (match.group(0) if match else 'B'
) # Default to "INCORRECT" if no match
return grade_letter
def medbullets_llmjudge_postprocess(
output: dict,
output_path: str,
dataset: Dataset,
) -> dict:
original_dataset = dataset.reader.dataset['test']
judged_answers = []
original_responses = []
references = []
details = []
# Initialize statistics dictionaries
stats = {'question_type': {}}
total_correct = 0
total_count = 0
# Process each sample
for k, v in output.items():
idx = int(k) # Convert key to integer for indexing
original_responses.append(v['prediction'])
processed_judge = _generic_llmjudge_postprocess(v['prediction'])
# Get category information from the dataset
sample = original_dataset[idx]
question_type = sample.get('question_type', 'unknown')
# Initialize category stats if not exists
for level, key in [
('question_type', question_type),
]:
if key not in stats[level]:
stats[level][key] = {'correct': 0, 'total': 0}
# Record the judgment
if processed_judge is not None:
judged_answers.append(processed_judge)
try:
gold = v['gold']
references.append(gold)
except KeyError:
get_logger().warning(
f'No gold answer for {k}, use empty string as reference!')
gold = ''
references.append('')
# Check if the answer is correct (A means correct)
is_correct = processed_judge == 'A'
total_count += 1
if is_correct:
total_correct += 1
# Update category stats
for level, key in [
('question_type', question_type),
]:
stats[level][key]['correct'] += 1
# Update category totals
for level, key in [
('question_type', question_type),
]:
stats[level][key]['total'] += 1
# Add to details
details.append({
'id': k,
'origin_prompt': v['origin_prompt'],
'llm_judge': processed_judge,
'gold': gold,
'is_correct': is_correct,
'question_type': question_type,
})
# Calculate overall accuracy with two decimal places
overall_accuracy = (round(
(total_correct / total_count * 100), 2) if total_count > 0 else 0.00)
# Initialize results dictionary
results = {
'accuracy': overall_accuracy,
'total_correct': total_correct,
'total_count': total_count,
'details': details,
}
# Calculate accuracy for each category and flatten into results
for level in stats:
for key, value in stats[level].items():
if value['total'] > 0:
# Calculate accuracy with two decimal places
accuracy = round((value['correct'] / value['total'] * 100), 2)
# Create a flattened key for the category
flat_key = f'Medbullets-{key}'
# Add to results
results[flat_key] = accuracy
return results

2
opencompass/datasets/__init__.py
View File

@ -99,8 +99,10 @@ from .mathbench import * # noqa: F401, F403
from .mbpp import * # noqa: F401, F403
from .mbpp_pro import * # noqa: F401, F403
from .medbench import * # noqa: F401, F403
from .Medbullets import * # noqa: F401, F403
from .MedCalc_Bench import MedCalc_BenchDataset # noqa: F401
from .MedCalc_Bench import MedCalcOfficial_Evaluator # noqa: F401
from .medmcqa import * # noqa: F401, F403
from .MedQA import * # noqa: F401, F403
from .MedXpertQA import * # noqa: F401, F403
from .mgsm import * # noqa: F401, F403

247
opencompass/datasets/medmcqa.py Normal file
View File

@ -0,0 +1,247 @@
import re
from datasets import Dataset, load_dataset
from opencompass.openicl import BaseEvaluator
from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
from opencompass.utils import get_logger
from .base import BaseDataset
def _parse(item, prompt_mode):
options_list = [item['opa'], item['opb'], item['opc'], item['opd']]
item['options'] = options_list
# 构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)])
# 将选项附加到问题末尾
item['question'] = f"{item['question']}\n{options_str}"
item['label'] = chr(65 + item['cop'])
item['subject_name'] = item['subject_name'].replace('_', ' ')
item['prompt_mode'] = prompt_mode
item['start'] = chr(65)
item['end'] = chr(65 + len(options_list) - 1) # 使用实际选项数量
return item
@LOAD_DATASET.register_module()
class MedmcqaDataset(BaseDataset):
@staticmethod
def load(path: str, prompt_mode: str = 'zero-shot', **kwargs):
dataset = load_dataset(path=path,
split='validation',
trust_remote_code=True)
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
return dataset
class MedmcqaEvaluator(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_name': test_set['subject_name'][idx],
'topic_name': test_set['topic_name'][idx],
'choice_type': test_set['choice_type'][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]
def _generic_llmjudge_postprocess(judgement: str):
match = re.search(r'(A|B)', judgement)
grade_letter = (match.group(0) if match else 'B'
) # Default to "INCORRECT" if no match
return grade_letter
def medmcqa_llmjudge_postprocess(
output: dict,
output_path: str,
dataset: Dataset,
) -> dict:
# Get the original dataset
original_dataset = dataset.reader.dataset['test']
judged_answers = []
original_responses = []
references = []
details = []
# Initialize statistics dictionaries
stats = {'subject': {}, 'topic': {}, 'question_type': {}}
total_correct = 0
total_count = 0
# Process each sample
for k, v in output.items():
idx = int(k) # Convert key to integer for indexing
original_responses.append(v['prediction'])
processed_judge = _generic_llmjudge_postprocess(v['prediction'])
# Get category information from the dataset
sample = original_dataset[idx]
subject = sample.get('subject_name', 'unknown')
question_type = sample.get('choice_type', 'unknown')
topic = sample.get('topic_name', 'unknown')
# Initialize category stats if not exists
for level, key in [
('subject', subject),
('question_type', question_type),
('topic', topic),
]:
if key not in stats[level]:
stats[level][key] = {'correct': 0, 'total': 0}
# Record the judgment
if processed_judge is not None:
judged_answers.append(processed_judge)
try:
gold = v['gold']
references.append(gold)
except KeyError:
get_logger().warning(
f'No gold answer for {k}, use empty string as reference!')
gold = ''
references.append('')
# Check if the answer is correct (A means correct)
is_correct = processed_judge == 'A'
total_count += 1
if is_correct:
total_correct += 1
# Update category stats
for level, key in [
('subject', subject),
('question_type', question_type),
('topic', topic),
]:
stats[level][key]['correct'] += 1
# Update category totals
for level, key in [
('subject', subject),
('question_type', question_type),
('topic', topic),
]:
stats[level][key]['total'] += 1
# Add to details
details.append({
'id': k,
'question': sample['question'],
'options': sample['options'],
'origin_prompt': v['origin_prompt'],
'llm_judge': processed_judge,
'gold': gold,
'is_correct': is_correct,
'subject': subject,
'question_type': question_type,
'topic': topic,
})
# Calculate overall accuracy with two decimal places
overall_accuracy = (round(
(total_correct / total_count * 100), 2) if total_count > 0 else 0.00)
# Initialize results dictionary
results = {
'accuracy': overall_accuracy,
'total_correct': total_correct,
'total_count': total_count,
'details': details,
}
# Calculate accuracy for each category and flatten into results
for level in stats:
for key, value in stats[level].items():
if value['total'] > 0:
# Calculate accuracy with two decimal places
accuracy = round((value['correct'] / value['total'] * 100), 2)
# Create a flattened key for the category
flat_key = f'medmcqa-{key}'
# Add to results
results[flat_key] = accuracy
return results

10
opencompass/utils/datasets_info.py
View File

@ -461,6 +461,12 @@ DATASETS_MAPPING = {
"hf_id": "",
"local": "./data/mbpp_pro/mbpp_pro.json",
},
"opencompass/medbullets": {
"ms_id": "",
"hf_id": "",
"local": "./data/medbullets/medbullets.csv",
},
}
DATASETS_URL = {
@ -826,4 +832,8 @@ DATASETS_URL = {
"url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/mbpp_pro.zip",
"md5": "eac330b8a0a8687f006265c9383503ce",
},
"medbullets": {
"url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/medbullets.zip",
"md5": "b63130999c1f28d57acba1c7852639f8",
},
}