99s42m/QAWithoutRAGLLMPrompts
收藏Hugging Face2024-07-02 更新2024-07-06 收录
下载链接：
https://hf-mirror.com/datasets/99s42m/QAWithoutRAGLLMPrompts
下载链接
链接失效反馈官方服务：
资源简介：
这是一个用于检测大型语言模型（LLM）幻觉的清洗和整合的问题（无上下文）和答案集。数据集中的每个问题-答案对并非作者原创，而是从以下数据集中选取的：Truthful QA（多项选择）、Truthful QA（文本生成）、Trivia QA和ARC。使用该数据集时，请引用上述来源以及相关论文。数据集由Shreyan Mitra整理，使用的语言为英语。使用方法包括将问题输入到选择的LLM中，并计算LLM生成的响应与给定答案的相似性来检测幻觉。
A cleaned and consolidated set of questions (without context) and answers for LLM hallucination detection. These question-answer pairs are not the work of the author, but were selected from datasets such as Truthful QA (Multiple Choice), Truthful QA (Text Generation), Trivia QA, and ARC. The dataset is curated by Shreyan Mitra and is in English. The primary use of the dataset is to detect hallucinations by feeding the questions into the chosen LLM and calculating the similarity of the LLM-generated response with the correct response provided in the answers column.
提供机构：
99s42m
