发表机构
Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Madeleine通过离线模拟生活学习记忆关联，在线零LLM调用，仅替换查询编码器，在LoCoMo-Plus上达到最高分并大幅提升基线。
AI 中文摘要
长期对话助手必须在正确的时刻回忆起正确的记忆，然而最重要的记忆往往与用户当前所说的话并不相似。现有系统通过在写入或读取时让大语言模型（LLM）进行推理来恢复此类关联，代价是每个记忆库需要数百到超过一千次LLM调用，以及每次查询最多数千个上下文令牌。我们认为关联是一种可学习的相关性：即记忆在人类生活展开方式下的点互信息。我们引入了Madeleine，它学习摊销关联：离线时，一个LLM生活模拟器编写模拟生活，其线索-触发对教会查询编码器在冻结的相似性之上学习残差关联；在线时，它不调用LLM，并通过仅替换查询编码器插入任何向量记忆库。在官方协议下的LoCoMo-Plus上，Madeleine（I）插入HyperMem时达到66.6，是该协议下所有评估系统中的最高分；（II）单独使用时，达到HyperMem发布时的分数（52.4对52.9），且零LLM调用，答案上下文约为其1/21；（III）将T-Mem提升26.2分，显著优于两个系统内部相同的未训练骨干，并在4B骨干上保持普通问答不变。
英文摘要
A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says now. Current systems recover such associations by letting an LLM reason at write or read time, at a cost of hundreds to over a thousand LLM calls per memory bank and up to several thousand context tokens per query. We argue that association is a learnable relevance: the pointwise mutual information of memories under how human lives unfold. We introduce Madeleine, which learns amortized association: offline, an LLM life simulator writes simulated lives, whose cue-trigger pairs teach a query encoder a residual association on top of frozen similarity; online, it calls no LLM and plugs into any vector memory by replacing only the query encoder. On LoCoMo-Plus under the official protocol, Madeleine (I) reaches 66.6 when plugged into HyperMem, the highest among all systems evaluated under this protocol; (II) used alone, reaches the score of HyperMem as released (52.4 vs. 52.9) with zero LLM calls and about 1/21 of its answer context; and (III) lifts T-Mem by 26.2 points, significantly outperforms the same untrained backbone inside both systems, and leaves ordinary QA intact on the 4B backbone.
Comments18 pages, 4 figures. v2: adds three-seed results for the HyperMem plug-in and an evaluation with human-written triggers (Appendix D)
