用联想图结构提升大模型对话记忆召回准确率
AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
- 构建对话线索关联图，模拟人类联想记忆
- 多信号融合使问答准确率在三个基准上均超越现有方法
- 适合需要长期上下文理解的对话系统研发者
从大规模记忆中实现精准召回仍是增强型AI助手进行问答的核心挑战，尤其在语义密集场景下，现有方法主要依赖查询与记忆间的语义距离。受人类信息联想方式启发，我们提出AssoMem框架，通过将对话话语锚定到自动提取的线索上，构建关联记忆图。该结构提供了丰富的对话上下文组织视图，并支持重要性感知排序。此外，AssoMem采用自适应互信息驱动的融合策略，整合相关性、重要性和时间对齐三种检索信号。在三个基准数据集和新提出的MeetingQA数据集上的大量实验表明，AssoMem始终优于当前最优基线，验证了其在上下文感知记忆召回方面的优势。
原文摘要 · Abstract (English)
Accurate recall from large scale memories remains a core challenge for memory augmented AI assistants performing question answering (QA), especially in similarity dense scenarios where existing methods mainly rely on semantic distance to the query for retrieval. Inspired by how humans link information associatively, we propose AssoMem, a novel framework constructing an associative memory graph that anchors dialogue utterances to automatically extracted clues. This structure provides a rich organizational view of the conversational context and facilitates importance aware ranking. Further, AssoMem integrates multi-dimensional retrieval signals-relevance, importance, and temporal alignment using an adaptive mutual information (MI) driven fusion strategy. Extensive experiments across three benchmarks and a newly introduced dataset, MeetingQA, demonstrate that AssoMem consistently outperforms SOTA baselines, verifying its superiority in context-aware memory recall.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。