arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04787cs.CLcs.AI
收藏

通过融合与精炼过去实现持续进化的记忆

Ever-Evolving Memory by Blending and Refining the Past

Yonsei University(延世大学);Seoul National University(首尔大学)

Seo Hyun Kim, Keummin Ka, Yohan Jo, Seung-won Hwang, Dongha Lee, Jinyoung Yeo

AI总结:

针对大语言模型长期记忆不足的问题,提出CREEM记忆系统,通过融合过去记忆并精炼冗余过时信息,将记忆构建与回复生成联合优化,提升多会话个性化对话效果。

摘要:

对于类人聊天机器人而言,构建长期记忆至关重要。然而,当前的大型语言模型往往缺乏这一能力,导致遗漏重要用户信息或重复询问相同信息的情况,从而降低对话质量。为有效构建记忆,关键在于无缝连接过去与现在的信息,同时具备遗忘阻碍性信息的能力。为应对这些挑战,我们提出了CREEM,一种用于长期对话的新型记忆系统。现有方法仅基于当前会话构建记忆,CREEM对此加以改进,在记忆形成过程中融合过去的记忆。此外,我们引入精炼流程以处理冗余或过时的信息。与传统范式不同,我们将回复和记忆构建视为不可分割的任务。生成新记忆的融合过程,还通过揭示过去与现在之间的联系,充当回复生成的推理步骤。通过评估,我们证明CREEM在多会话个性化对话中同时提升了记忆质量和回复质量。

英文摘要:

For a human-like chatbot, constructing a long-term memory is crucial. However, current large language models often lack this capability, leading to instances of missing important user information or redundantly asking for the same information, thereby diminishing conversation quality. To effectively construct memory, it is crucial to seamlessly connect past and present information, while also possessing the ability to forget obstructive information. To address these challenges, we propose CREEM, a novel memory system for long-term conversation. Improving upon existing approaches that construct memory based solely on current sessions, CREEM blends past memories during memory formation. Additionally, we introduce a refining process to handle redundant or outdated information. Unlike traditional paradigms, we view responding and memory construction as inseparable tasks. The blending process, which creates new memories, also serves as a reasoning step for response generation by informing the connection between past and present. Through evaluation, we demonstrate that CREEM enhances both memory and response qualities in multi-session personalized dialogues.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑