[Dataset] Add MedXpertQA (#2002)

* Add MedXpertQA

* Add MedXpertQA

* Add MedXpertQA

* Fix lint

---------

Co-authored-by: MaiziXiao <xxllcc1993@gmail.com>

.pre-commit-config-zh-cn.yaml

@@ -120,4 +120,4 @@ repos:
   #   hooks:
   #     - id: check-algo-readme
       # - id: check-copyright
-      #   args: ["mmocr", "tests", "tools"]  # these directories will be checked
+      #   args: ["mmocr", "tests", "tools"]  # these directories will be checked

.pre-commit-config.yaml

@@ -120,4 +120,4 @@ repos:
   #   hooks:
   #     - id: check-algo-readme
       # - id: check-copyright
-      #   args: ["mmocr", "tests", "tools"]  # these directories will be checked
+      #   args: ["mmocr", "tests", "tools"]  # these directories will be checked

dataset-index.yml

@@ -116,6 +116,12 @@
     paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10778138
     configpath: opencompass/configs/datasets/MedBench/medbench_gen.py
     configpath_llmjudge: ''
+- MedXpertQA:
+    name: MedXpertQA
+    category: Knowledge / Medicine
+    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
 - musr:
     name: MuSR
     category: Reasoning

opencompass/configs/datasets/MedXpertQA/MedXpertQA_gen.py

@@ -0,0 +1,57 @@
+from opencompass.datasets import MedXpertQADataset, MedXpertQAEvaluator
+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}\nA: Among {start} through {end}, the answer is'
+
+# Reader configuration
+reader_cfg = dict(
+    input_columns=[
+        'question',
+        'options',
+        'medical_task',
+        'body_system',
+        '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=MedXpertQAEvaluator),
+    pred_role='BOT',
+)
+medxpertqa_dataset = dict(
+    type=MedXpertQADataset,
+    abbr='medxpertqa',
+    path='TsinghuaC3I/MedXpertQA',
+    prompt_mode='zero-shot',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg,
+)
+
+medxpertqa_datasets = [medxpertqa_dataset]

opencompass/configs/datasets/MedXpertQA/MedXpertQA_llmjudge_gen.py

@@ -0,0 +1,104 @@
+from opencompass.datasets import MedXpertQADataset, MedXpertQA_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}\nA: Among {start} through {end}, the answer is'
+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}\nA: Among {start} through {end}, the answer is\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',
+        'medical_task',
+        'body_system',
+        '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=MedXpertQADataset,
+            path='TsinghuaC3I/MedXpertQA',
+            prompt_mode='zero-shot',
+            reader_cfg=reader_cfg,
+        ),
+        judge_cfg=dict(),
+        dict_postprocessor=dict(type=MedXpertQA_llmjudge_postprocess),
+    ),
+)
+medxpertqa_dataset = dict(
+    type=MedXpertQADataset,
+    abbr='medxpertqa',
+    path='TsinghuaC3I/MedXpertQA',
+    prompt_mode='zero-shot',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg,
+)
+
+medxpertqa_datasets = [medxpertqa_dataset]

opencompass/datasets/MedXpertQA.py

@@ -0,0 +1,225 @@
+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):
+    item['start'] = chr(65)
+    item['end'] = chr(65 + len(item.get('options', [])) - 1)
+    item['prompt_mode'] = prompt_mode
+    return item
+
+
+@LOAD_DATASET.register_module()
+class MedXpertQADataset(BaseDataset):
+
+    @staticmethod
+    def load(path: str, prompt_mode: str, **kwargs):
+        dataset = load_dataset(path, 'Text', split='test')
+        # dataset = load_dataset(path, 'Text', split='dev')
+
+        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 MedXpertQAEvaluator(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}
+            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 = []
+    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 MedXpertQA_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 = {'medical_task': {}, 'body_system': {}, '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]
+        medical_task = sample.get('medical_task', 'unknown')
+        body_system = sample.get('body_system', 'unknown')
+        question_type = sample.get('question_type', 'unknown')
+
+        # Initialize category stats if not exists
+        for level, key in [
+            ('medical_task', medical_task),
+            ('body_system', body_system),
+            ('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 [
+                    ('medical_task', medical_task),
+                    ('body_system', body_system),
+                    ('question_type', question_type),
+                ]:
+                    stats[level][key]['correct'] += 1
+
+            # Update category totals
+            for level, key in [
+                ('medical_task', medical_task),
+                ('body_system', body_system),
+                ('question_type', question_type),
+            ]:
+                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,
+                'medical_task': medical_task,
+                'body_system': body_system,
+                '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'MedXpertQA-{key}'
+
+                # Add to results
+                results[flat_key] = accuracy
+
+    return results

opencompass/datasets/__init__.py

@@ -92,6 +92,7 @@ from .math_intern import *  # noqa: F401, F403
 from .mathbench import *  # noqa: F401, F403
 from .mbpp import *  # noqa: F401, F403
 from .medbench import *  # noqa: F401, F403
+from .MedXpertQA import *  # noqa: F401, F403
 from .mgsm import *  # noqa: F401, F403
 from .mmlu import *  # noqa: F401, F403
 from .mmlu_cf import *  # noqa: F401, F403