将记忆摘要基于效用意图
Grounding Memory Summarization in Utility Intent
- University of Virginia（弗吉尼亚大学）
- Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对记忆摘要与下游查询效用错位的问题，提出MemSuit自蒸馏框架，通过问答对调节生成效用感知条目并微调检索器，显著提升答案质量。
AI中文摘要：
现有的记忆系统摘要器通常针对人类可读性标准（如忠实度）进行优化，这与它们的真实目标——保留支持未来查询所需的证据——不一致。我们证明，基于问答对来调节摘要能显著提高答案质量，并且这种效用感知行为可跨查询迁移。受这些发现启发，我们提出了MemSuit，一种自蒸馏框架，其中教师摘要器基于观察到的问答对生成效用感知的记忆条目，而学生则仅从原始对话中学习复现这些条目。为防止附带性擦除（即基于单个问答对进行调节会丢弃与其他合理查询相关的证据），教师将每个对话块分解为多个自包含条目，将不同的查询相关方面保留为独立可检索的单元。为使检索器与教师条目的紧凑、事实密集风格对齐，我们进一步使用由教师条目监督的对比目标对嵌入模型进行微调。在多种对话查询类型中，MemSuit始终优于最先进的基线，证实了将记忆基于下游效用的价值。
英文摘要：
Existing summarizers for memory systems are typically optimized for human-facing criteria such as faithfulness, which misaligns with their true objective: preserving the evidence needed to support future queries. We show that conditioning summarization on query-answer pairs substantially improves answer quality, and that this utility-aware behavior is transferable across queries. Motivated by these findings, we propose MemSuit, a self-distillation framework in which a teacher summarizer, conditioned on observed query-answer pairs, produces utility-aware memory entries that a student learns to reproduce from the raw conversation alone. To prevent collateral erasure where conditioning on a single query-answer pair discards evidence relevant to other plausible queries, the teacher decomposes each block into multiple self-contained entries that preserve distinct query-relevant facets as independently retrievable units. To align the retriever with the compact, fact-dense style of teacher entries, we further fine-tune the embedding model with a contrastive objective supervised by teacher entries. Across a diverse suite of conversational query types, MemSuit consistently outperforms state-of-the-art baselines, confirming the value of grounding memory in downstream utility.
