THEANINE：通过时间轴增强响应生成重新审视长期对话中的记忆管理

THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation

June 16, 2024

作者: Seo Hyun Kim, Kai Tzu-iunn Ong, Taeyoon Kwon, Namyoung Kim, Keummin Ka, SeongHyeon Bae, Yohan Jo, Seung-won Hwang, Dongha Lee, Jinyoung Yeo

cs.AI

摘要

大型语言模型（LLMs）能够在与用户长时间互动过程中处理漫长的对话历史，而无需额外的记忆模块；然而，它们的回复往往会忽视或错误地回忆起过去的信息。在本文中，我们重新审视了在LLMs时代中增强记忆的响应生成。虽然先前的工作侧重于摆脱过时的记忆，但我们认为这些记忆可以提供上下文线索，帮助对话系统理解过去事件的发展，从而有助于响应生成。我们提出Theanine，这是一个框架，通过记忆时间线（展示相关过去事件发展和因果关系的一系列记忆）来增强LLMs的响应生成。除了Theanine，我们还介绍了TeaFarm，这是一个以反事实驱动的问答流程，解决了长期对话中G-Eval的局限性。我们的方法的补充视频和用于TeaFarm评估的TeaBag数据集可在https://theanine-693b0.web.app/找到。

English

Large language models (LLMs) are capable of processing lengthy dialogue histories during prolonged interaction with users without additional memory modules; however, their responses tend to overlook or incorrectly recall information from the past. In this paper, we revisit memory-augmented response generation in the era of LLMs. While prior work focuses on getting rid of outdated memories, we argue that such memories can provide contextual cues that help dialogue systems understand the development of past events and, therefore, benefit response generation. We present Theanine, a framework that augments LLMs' response generation with memory timelines -- series of memories that demonstrate the development and causality of relevant past events. Along with Theanine, we introduce TeaFarm, a counterfactual-driven question-answering pipeline addressing the limitation of G-Eval in long-term conversations. Supplementary videos of our methods and the TeaBag dataset for TeaFarm evaluation are in https://theanine-693b0.web.app/.