MemGuard：防止长期记忆增强型大语言模型中的记忆污染
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
AI总结：
提出MemGuard，一种类型感知的记忆框架，通过显式分配功能角色、维护类型隔离记忆间的关联并选择性组合必要类型的证据，防止异构记忆污染，提升记忆可靠性最高28.27%并减少检索token数最高5.8倍。
摘要：
记忆增强型大语言模型通过跨交互维护长期记忆，将推理扩展到固定上下文窗口之外。然而，现有的记忆系统常常将稳定的用户事实、情景事件和行为规则折叠到共享空间中，使得功能不同的记忆被检索并用作可互换的证据。我们将这种失败模式识别为异构记忆污染，其中上下文特定的事件被过度概括为声明，或者语义相关但功能不兼容的记忆误导生成。为此，我们引入了MemGuard，一种类型感知的记忆框架，在记忆构建和检索过程中保留功能记忆边界。它在写入时为每个记忆分配显式的功能角色，维护跨类型隔离记忆的关系，并仅从必要的记忆类型中选择性组合证据，从而减少来自无关或功能不兼容证据的污染。在幻觉和长时对话基准测试中，MemGuard将记忆可靠性提高了最多28.27%，同时检索的记忆token数比先前方法减少了最多5.8倍。这些结果表明，可靠的长期推理依赖于对异构记忆的有原则的组织和选择性使用。
英文摘要：
Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral rules into a shared space, allowing functionally distinct memories to be retrieved and used as interchangeable evidence. We identify this failure mode as heterogeneous memory contamination, where context-specific events become overgeneralized claims, or semantically relevant but functionally incompatible memories mislead generation. To this end, we introduce MemGuard, a type-aware memory framework that preserves functional memory boundaries during memory construction and retrieval. It assigns each memory an explicit functional role at write time, maintains relations across type-isolated memories, and selectively composes evidence only from necessary memory types, reducing contamination from irrelevant or functionally incompatible evidence. Across hallucination and long-horizon conversation benchmarks, MemGuard improves memory reliability by up to 28.27% while retrieving up to 5.8x fewer memory tokens than prior methods. These results suggest that reliable long-term reasoning depends on principled organization and selective use of heterogeneous memory.
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。
