From 9ec23c145b4c0ac441b51d6e326e2074975b2400 Mon Sep 17 00:00:00 2001 From: Jiahao Xu <48542487+xuxuxuxuxuxjh@users.noreply.github.com> Date: Thu, 8 May 2025 16:25:43 +0800 Subject: [PATCH] [Datasets] Add ClinicBench, PubMedQA and ScienceQA (#2061) * Add ClinicBench * Add PubMedQA & ScienceQA & ClinicBench * Add PubMedQA & ScienceQA & ClinicBench * Update datasets_info & hf_path * Update hf_path --- dataset-index.yml | 18 ++++ .../ClinicBench/ClinicBench_llmjudge_gen.py | 4 + .../ClinicBench_llmjudge_gen_d09668.py | 100 ++++++++++++++++++ .../PubMedQA/PubMedQA_llmjudge_gen.py | 4 + .../PubMedQA/PubMedQA_llmjudge_gen_f00302.py | 94 ++++++++++++++++ .../ScienceQA/ScienceQA_llmjudge_gen.py | 4 + .../ScienceQA_llmjudge_gen_f00302.py | 94 ++++++++++++++++ opencompass/datasets/ClinicBench.py | 19 ++++ opencompass/datasets/PubMedQA.py | 34 ++++++ opencompass/datasets/ScienceQA.py | 32 ++++++ 10 files changed, 403 insertions(+) create mode 100644 opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen.py create mode 100644 opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen_d09668.py create mode 100644 opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen.py create mode 100644 opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen_f00302.py create mode 100644 opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen.py create mode 100644 opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen_f00302.py create mode 100644 opencompass/datasets/ClinicBench.py create mode 100644 opencompass/datasets/PubMedQA.py create mode 100644 opencompass/datasets/ScienceQA.py diff --git a/dataset-index.yml b/dataset-index.yml index 4a920071..94e88200 100644 --- a/dataset-index.yml +++ b/dataset-index.yml @@ -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 diff --git a/opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen.py b/opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen.py new file mode 100644 index 00000000..febfce11 --- /dev/null +++ b/opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen.py @@ -0,0 +1,4 @@ +from mmengine.config import read_base + +with read_base(): + from .ClinicBench_llmjudge_gen_d09668 import ClinicBench_datasets \ No newline at end of file diff --git a/opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen_d09668.py b/opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen_d09668.py new file mode 100644 index 00000000..358a91f5 --- /dev/null +++ b/opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen_d09668.py @@ -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. + + : {question}\n {choices} \n\n\n + : \n{label}\n\n\n + : \n{prediction}\n\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, + ) +) diff --git a/opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen.py b/opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen.py new file mode 100644 index 00000000..4055d0f5 --- /dev/null +++ b/opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen.py @@ -0,0 +1,4 @@ +from mmengine.config import read_base + +with read_base(): + from .PubMedQA_llmjudge_gen_f00302 import PubMedQA_datasets \ No newline at end of file diff --git a/opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen_f00302.py b/opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen_f00302.py new file mode 100644 index 00000000..b38a8fe5 --- /dev/null +++ b/opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen_f00302.py @@ -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. + : {question}\n {choices} \n\n\n + : \n{label}\n\n\n + : \n{prediction}\n\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, + ) +) \ No newline at end of file diff --git a/opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen.py b/opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen.py new file mode 100644 index 00000000..32305456 --- /dev/null +++ b/opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen.py @@ -0,0 +1,4 @@ +from mmengine.config import read_base + +with read_base(): + from .ScienceQA_llmjudge_gen_f00302 import ScienceQA_datasets \ No newline at end of file diff --git a/opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen_f00302.py b/opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen_f00302.py new file mode 100644 index 00000000..e128c2a0 --- /dev/null +++ b/opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen_f00302.py @@ -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. + : {question}\n {choices} \n\n\n + : \n{label}\n\n\n + : \n{prediction}\n\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, + ) +) \ No newline at end of file diff --git a/opencompass/datasets/ClinicBench.py b/opencompass/datasets/ClinicBench.py new file mode 100644 index 00000000..86ef5082 --- /dev/null +++ b/opencompass/datasets/ClinicBench.py @@ -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 diff --git a/opencompass/datasets/PubMedQA.py b/opencompass/datasets/PubMedQA.py new file mode 100644 index 00000000..b0db32e3 --- /dev/null +++ b/opencompass/datasets/PubMedQA.py @@ -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 diff --git a/opencompass/datasets/ScienceQA.py b/opencompass/datasets/ScienceQA.py new file mode 100644 index 00000000..1bc9c952 --- /dev/null +++ b/opencompass/datasets/ScienceQA.py @@ -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