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 1/4] [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 From a685ed7daffcab6b7cfb27ba1332242e403d138f Mon Sep 17 00:00:00 2001 From: Wei Li <1253865871@qq.com> Date: Thu, 8 May 2025 16:44:05 +0800 Subject: [PATCH 2/4] [Dataset] Add nejm ai benchmark (#2063) * support nejm ai benchmark * add dataset files * revise gen name * revise gen name * revise class name & remove csv file & add dataset-index.yml info * update * update --------- Co-authored-by: MaiziXiao --- dataset-index.yml | 8 +- .../nejm_ai_benchmark/nejmaibench_gen.py | 4 + .../nejmaibench_gen_60c8f5.py | 59 ++++++++ .../nejmaibench_llmjudge_gen.py | 4 + .../nejmaibench_llmjudge_gen_60c8f5.py | 108 ++++++++++++++ opencompass/datasets/__init__.py | 1 + opencompass/datasets/nejmaibench.py | 139 ++++++++++++++++++ opencompass/utils/datasets_info.py | 10 ++ 8 files changed, 332 insertions(+), 1 deletion(-) create mode 100644 opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen.py create mode 100644 opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen_60c8f5.py create mode 100644 opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen.py create mode 100644 opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen_60c8f5.py create mode 100644 opencompass/datasets/nejmaibench.py diff --git a/dataset-index.yml b/dataset-index.yml index 94e88200..1bfbdbbc 100644 --- a/dataset-index.yml +++ b/dataset-index.yml @@ -1046,4 +1046,10 @@ category: Reasoning/Code/Agent paper: '' configpath: opencompass/configs/datasets/internsandbox/internsandbox_gen_44b982.py - configpath_llmjudge: '' \ No newline at end of file + 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 diff --git a/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen.py b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen.py new file mode 100644 index 00000000..2116726c --- /dev/null +++ b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen.py @@ -0,0 +1,4 @@ +from mmengine.config import read_base + +with read_base(): + from .nejmaibench_gen_60c8f5 import nejmaibench_datasets # noqa: F401, F403 \ No newline at end of file diff --git a/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen_60c8f5.py b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen_60c8f5.py new file mode 100644 index 00000000..ec817c57 --- /dev/null +++ b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen_60c8f5.py @@ -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] diff --git a/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen.py b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen.py new file mode 100644 index 00000000..de683ccc --- /dev/null +++ b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen.py @@ -0,0 +1,4 @@ +from mmengine.config import read_base + +with read_base(): + from .nejmaibench_llmjudge_gen_60c8f5 import nejmaibench_datasets # noqa: F401, F403 \ No newline at end of file diff --git a/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen_60c8f5.py b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen_60c8f5.py new file mode 100644 index 00000000..31be8049 --- /dev/null +++ b/opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen_60c8f5.py @@ -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. + + : 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\n\n + : \n{label}\n\n\n + : \n{prediction}\n\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] diff --git a/opencompass/datasets/__init__.py b/opencompass/datasets/__init__.py index a7c037cf..220ce030 100644 --- a/opencompass/datasets/__init__.py +++ b/opencompass/datasets/__init__.py @@ -109,6 +109,7 @@ 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 diff --git a/opencompass/datasets/nejmaibench.py b/opencompass/datasets/nejmaibench.py new file mode 100644 index 00000000..768f4688 --- /dev/null +++ b/opencompass/datasets/nejmaibench.py @@ -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] diff --git a/opencompass/utils/datasets_info.py b/opencompass/utils/datasets_info.py index 5048a496..10ca4436 100644 --- a/opencompass/utils/datasets_info.py +++ b/opencompass/utils/datasets_info.py @@ -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", + }, } @@ -798,6 +803,11 @@ 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" } } From ff3275edf023f2ce49c3fbfed90ff675ca27c1c9 Mon Sep 17 00:00:00 2001 From: Mo Li <2568818204@qq.com> Date: Thu, 8 May 2025 19:06:56 +0800 Subject: [PATCH 3/4] [Update] Add Long-Context configs for Gemma, OREAL, and Qwen2.5 models (#2048) * [Update] Update Gemma, Oreal, Qwen Config * fix lint --- .../models/gemma/vllm_gemma_3_12b_it.py | 16 ++++++++++++++ .../models/gemma/vllm_gemma_3_27b_it.py | 16 ++++++++++++++ .../models/gemma/vllm_gemma_3_4b_it.py | 17 +++++++++++++++ .../lmdeploy_internlm3_8b_instruct_128k.py | 19 +++++++++++++++++ .../models/hf_internlm/lmdeploy_oreal_32b.py | 20 ++++++++++++++++++ .../qwen2_5/vllm_qwen2_5_14b_instruct_128k.py | 21 +++++++++++++++++++ .../qwen2_5/vllm_qwen2_5_32b_instruct_128k.py | 21 +++++++++++++++++++ .../qwen2_5/vllm_qwen2_5_72b_instruct_128k.py | 21 +++++++++++++++++++ .../qwen2_5/vllm_qwen2_5_7b_instruct_128k.py | 21 +++++++++++++++++++ 9 files changed, 172 insertions(+) create mode 100644 opencompass/configs/models/gemma/vllm_gemma_3_12b_it.py create mode 100644 opencompass/configs/models/gemma/vllm_gemma_3_27b_it.py create mode 100644 opencompass/configs/models/gemma/vllm_gemma_3_4b_it.py create mode 100644 opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct_128k.py create mode 100644 opencompass/configs/models/hf_internlm/lmdeploy_oreal_32b.py create mode 100644 opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct_128k.py create mode 100644 opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct_128k.py create mode 100644 opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct_128k.py create mode 100644 opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct_128k.py diff --git a/opencompass/configs/models/gemma/vllm_gemma_3_12b_it.py b/opencompass/configs/models/gemma/vllm_gemma_3_12b_it.py new file mode 100644 index 00000000..2914640f --- /dev/null +++ b/opencompass/configs/models/gemma/vllm_gemma_3_12b_it.py @@ -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), + ) +] diff --git a/opencompass/configs/models/gemma/vllm_gemma_3_27b_it.py b/opencompass/configs/models/gemma/vllm_gemma_3_27b_it.py new file mode 100644 index 00000000..b6f4b93b --- /dev/null +++ b/opencompass/configs/models/gemma/vllm_gemma_3_27b_it.py @@ -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), + ) +] diff --git a/opencompass/configs/models/gemma/vllm_gemma_3_4b_it.py b/opencompass/configs/models/gemma/vllm_gemma_3_4b_it.py new file mode 100644 index 00000000..22516ff7 --- /dev/null +++ b/opencompass/configs/models/gemma/vllm_gemma_3_4b_it.py @@ -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), + ) +] diff --git a/opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct_128k.py b/opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct_128k.py new file mode 100644 index 00000000..1cc4e251 --- /dev/null +++ b/opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct_128k.py @@ -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), + ) +] diff --git a/opencompass/configs/models/hf_internlm/lmdeploy_oreal_32b.py b/opencompass/configs/models/hf_internlm/lmdeploy_oreal_32b.py new file mode 100644 index 00000000..1d10bd94 --- /dev/null +++ b/opencompass/configs/models/hf_internlm/lmdeploy_oreal_32b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct_128k.py b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct_128k.py new file mode 100644 index 00000000..6dec3743 --- /dev/null +++ b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct_128k.py @@ -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), + ) +] diff --git a/opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct_128k.py b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct_128k.py new file mode 100644 index 00000000..5c326734 --- /dev/null +++ b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct_128k.py @@ -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), + ) +] diff --git a/opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct_128k.py b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct_128k.py new file mode 100644 index 00000000..2a4a52fa --- /dev/null +++ b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct_128k.py @@ -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), + ) +] diff --git a/opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct_128k.py b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct_128k.py new file mode 100644 index 00000000..db21f730 --- /dev/null +++ b/opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct_128k.py @@ -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), + ) +] From a7f3ac20b259339b851e4664991686161fa0d866 Mon Sep 17 00:00:00 2001 From: huihui1999 <107675879+bio-mlhui@users.noreply.github.com> Date: Thu, 8 May 2025 19:44:46 +0800 Subject: [PATCH 4/4] [Dataset] Add CARDBiomedBench (#2071) * CARDBiomedBench * fix hash * fix dataset-index * use official llmjudge postprocess * use official llmjudge_postprocess * fix lint * fix init --- dataset-index.yml | 6 ++ .../CARDBiomedBench_llmjudge_gen_99a231.py | 101 ++++++++++++++++++ opencompass/datasets/CARDBiomedBench.py | 30 ++++++ opencompass/datasets/__init__.py | 1 + 4 files changed, 138 insertions(+) create mode 100644 opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen_99a231.py create mode 100644 opencompass/datasets/CARDBiomedBench.py diff --git a/dataset-index.yml b/dataset-index.yml index 1bfbdbbc..f0960740 100644 --- a/dataset-index.yml +++ b/dataset-index.yml @@ -361,6 +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 diff --git a/opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen_99a231.py b/opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen_99a231.py new file mode 100644 index 00000000..c6acb71e --- /dev/null +++ b/opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen_99a231.py @@ -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. + + : Q: You are an expert in {expert}.\n{question}\n\n\n + : \n{answer}\n\n\n + : \n{prediction}\n\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] diff --git a/opencompass/datasets/CARDBiomedBench.py b/opencompass/datasets/CARDBiomedBench.py new file mode 100644 index 00000000..77ff9ee6 --- /dev/null +++ b/opencompass/datasets/CARDBiomedBench.py @@ -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 diff --git a/opencompass/datasets/__init__.py b/opencompass/datasets/__init__.py index 220ce030..03e7d228 100644 --- a/opencompass/datasets/__init__.py +++ b/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 CARDBiomedBenchDataset # noqa: F401 from .cb import * # noqa: F401, F403 from .ceval import * # noqa: F401, F403 from .charm import * # noqa: F401, F403