CARDBiomedBench

opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen.py

@@ -0,0 +1,101 @@
+from opencompass.datasets import CARDBiomedBenchDataset, CARDBiomedBench_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=CARDBiomedBench_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]

opencompass/datasets/CARDBiomedBench.py

@@ -0,0 +1,107 @@
+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['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
+
+
+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 CARDBiomedBench_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 = []
+
+    total_correct = 0
+    total_count = 0
+
+    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'])
+
+        sample = original_dataset[idx]
+        # 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
+
+            # Add to details
+            details.append({
+                'id': k,
+                'question': sample['question'],
+                'prediction': sample['prediction'],
+                'origin_prompt': v['origin_prompt'],
+                'llm_judge': processed_judge,
+                'gold': gold,
+                'is_correct': is_correct,
+            })
+
+    # 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,
+    }
+    return results

opencompass/datasets/__init__.py

@@ -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 *
 from .cb import *  # noqa: F401, F403
 from .ceval import *  # noqa: F401, F403
 from .charm import *  # noqa: F401, F403