zli12321/pedants_qa_evaluation_bench
收藏Hugging Face2024-12-16 更新2024-12-21 收录
下载链接：
https://hf-mirror.com/datasets/zli12321/pedants_qa_evaluation_bench
下载链接
链接失效反馈官方服务：
资源简介：
该数据集用于评估多个问答任务（如Jeopardy、hotpotQA、nq-open、narrativeQA和BIOMRC等）中的候选答案。它包含问题、参考答案（正确答案）、模型生成的候选答案以及人类对候选答案是否正确的判断。数据集的列信息包括问题、参考答案、候选答案、标签、模型、数据集来源和问题上下文。
This dataset evaluates candidate answers for various question-answering (QA) tasks across multiple datasets such as Jeopardy!, hotpotQA, nq-open, narrativeQA, and BIOMRC, etc. It contains questions, reference answers (ground truth), model-generated candidate answers, and human judgments indicating whether the candidate answers are correct.
提供机构：
zli12321
