arXiv / Factual Memory / Token-level

MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation

作者：Junru Lu, Siyu An, Mingbao Lin, Gabriele Pergola, Yulan He, Di Yin, Xing Sun, Yunsheng Wu · 单位：University of Warwick, 2Tecent YouTu Lab, 3King’s College London · 来源：arXiv · 发布日期：2023/08

事实记忆词元级记忆
新标签打开 AlphaXiv
MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation figure
AlphaXiv 中文概览（可滚动查看）