zihanz/RetrievalQA
收藏数据集概述
RetrievalQA 是一个短形式开放领域问答(QA)数据集,包含1,271个问题,涵盖新世界和长尾知识。该数据集确保了回答问题所需的知识在大多数大型语言模型(LLMs)中不存在,因此LLMs必须真实地决定是否进行检索以正确回答问题。RetrievalQA 使我们能够评估**自适应检索增强生成(RAG)**方法的有效性,这一方面在先前的研究和最近的RAG评估系统中主要被忽视,这些系统仅关注任务性能、检索上下文的相关性或答案的忠实度。
数据集来源
- 仓库: https://github.com/hyintell/RetrievalQA
- 论文: https://arxiv.org/abs/2402.16457
数据集结构
以下是一个数据实例的示例:
json { "data_source": "realtimeqa", "question_id": "realtimeqa_20231013_1", "question": "What percentage of couples are sleep divorced, according to new research?", "ground_truth": ["15%"], "context": [ { "title": "Do We Sleep Longer When We Share a Bed?", "text": "1.4% of respondents have started a sleep divorce, or sleeping separately from their partner, and maintained it in the past year. Adults who have ..." }, ... ] }
其中:
data_source: 问题来源的数据集question: 问题ground_truth: 可能答案的列表context: 检索到的相关证据的列表,每个证据是一个字典,可能包含title和text字段,注意title可能为空。
引用
bibtex @misc{zhang2024retrievalqa, title={RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering}, author={Zihan Zhang and Meng Fang and Ling Chen}, year={2024}, eprint={2402.16457}, archivePrefix={arXiv}, primaryClass={cs.CL} }



