关于个性化对话智能体的记忆构建与检索
On Memory Construction and Retrieval for Personalized Conversational Agents
AI总结：
针对长期对话中记忆检索的局限性，提出SeCom方法，通过对话分割模型在片段级别构建记忆库并应用基于压缩的去噪机制，显著提升了个性化对话的记忆检索准确性与整体性能。
摘要：
为了在长期对话中提供连贯且个性化的体验，现有方法通常通过在轮次级别、会话级别或通过摘要技术从对话历史中构建记忆库，从而进行检索增强的回复生成。在本文中，我们提出两个关键发现：（1）记忆单元的粒度至关重要：轮次级别、会话级别和基于摘要的方法在记忆检索准确性和检索内容的语义质量上均存在局限性。（2）提示压缩方法（如LLMLingua-2）可以有效作为去噪机制，提升不同粒度下的记忆检索准确性。基于这些见解，我们提出了SeCom方法，该方法通过引入对话分割模型将长期对话划分为主题连贯的片段，从而在片段级别构建记忆库，同时对记忆单元应用基于压缩的去噪以增强记忆检索。实验结果表明，SeCom在长期对话基准LOCOMO和Long-MT-Bench+上表现出显著优于基线的性能优势。此外，所提出的对话分割方法在DialSeg711、TIAGE和SuperDialSeg等对话分割数据集上展现出优越的性能。
英文摘要：
To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques.In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content. (2) Prompt compression methods, such as LLMLingua-2, can effectively serve as a denoising mechanism, enhancing memory retrieval accuracy across different granularities. Building on these insights, we propose SeCom, a method that constructs the memory bank at segment level by introducing a conversation segmentation model that partitions long-term conversations into topically coherent segments, while applying compression based denoising on memory units to enhance memory retrieval. Experimental results show that SeCom exhibits a significant performance advantage over baselines on long-term conversation benchmarks LOCOMO and Long-MT-Bench+. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as DialSeg711, TIAGE, and SuperDialSeg.
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。
