TOFU
收藏AI_Studio2025-09-03 更新2025-08-23 收录
下载链接：
https://aistudio.baidu.com/datasetdetail/350844
下载链接
链接失效反馈官方服务：
资源简介：
专为评估大语言模型“遗忘”性能而设计的基准，包含虚构作者的问答对。
This benchmark is specifically designed to evaluate the "forgetting" performance of Large Language Models (LLMs), and it includes question-answer pairs from fictional authors.
提供机构：
皮都坦率的法夏
