发表机构
Tianjin University of Technology（天津理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出记忆决策层（MDL），通过三信号互补编码器解耦置信度与一致性，实现零参数白盒记忆信任决策，将冲突记忆下幻觉率降低56.04%，高风险场景接近零幻觉。
AI 中文摘要
大型语言模型的记忆系统主要关注高效检索，而对检索到的记忆是否应被信任的决策却关注较少。当记忆库包含相互冲突的立场时，标准检索增强生成（RAG）盲目注入记忆并放大幻觉：在易受记忆注入影响的模型中，冲突记忆下的RAG幻觉率明显高于无记忆基线。受前额叶皮层记忆信号机制的启发，我们提出了记忆决策层（MDL），一种位于检索和生成阶段之间的零参数记忆决策控制器。其核心是一个三信号互补编码器，通过基于QR的正交子空间投影和元工作记忆信号，将相关性、可靠性和任务风险融合为可解释的决策表示，以量化检索记忆的可信度。基于该编码器，MDL显式地解耦置信度与一致性，并引入风险反转和显式弃权（不执行）。在主流水准大语言模型和多个开源数据集上的评估表明，MDL在一般场景下将冲突记忆下的幻觉率降低约56.04%，在高风险场景下接近零幻觉。该控制器完全白盒：它纯粹依赖几何运算，无需训练参数，每次决策仅增加约0.14毫秒——比其前的嵌入检索步骤快约50倍，比LLM自评估调用快四到五个数量级。
英文摘要
Memory systems for large language models have focused predominantly on efficient retrieval, whereas the decision of whether retrieved memories should be trusted has received comparatively little attention. When the memory store contains conflicting positions, standard retrieval-augmented generation (RAG) blindly injects memories and amplifies hallucinations: in models susceptible to memory injection, the RAG hallucination rate under conflicting memories is markedly higher than that of a memory-free baseline. Inspired by memory signaling mechanisms in the prefrontal cortex, we propose the Memory Decision Layer (MDL), a zero-parameter memory decision controller situated between the retrieval and generation stages. Its core is a three-signal complementary encoder that fuses relevance, reliability, and task risk through QR-based orthogonal subspace projection and a meta-working-memory signal into an interpretable decision representation that quantifies the trustworthiness of retrieved memories. Building on this encoder, MDL explicitly decouples confidence from consistency and introduces risk inversion and explicit abstention. Evaluations on mainstream large language models and multiple open-source datasets show that MDL reduces the hallucination rate under conflicting memories by about 56.04% in general scenarios and approaches zero hallucination in high-risk scenarios. The controller is fully white-box: it relies purely on geometric operations, requires no trained parameters, and adds only about 0.14 ms per decision -- roughly 50x faster than the embedding-retrieval step that precedes it and four to five orders of magnitude faster than an LLM self-evaluation call.
Comments17 pages, 6 figures, 10 tables
