用生物突触机制提升大模型对时间分散对话的记忆检索准确率
SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms
- 结合时间关联触发与类突触信号传播，动态激活相关对话记忆
- 在中英日多语数据集上，相比顶尖方法提升达14.66%点
- 适合需要长时对话理解的智能客服、虚拟助手等场景
现有大模型的检索方法在处理时间分散对话时准确率下降，主要因依赖简单语义相似度。不同于仅依赖语义相似的现有记忆检索方法，我们提出SynapticRAG，首次将时间关联触发与类生物突触的信号传播机制结合。该方法利用时间关联触发和类突触刺激传播识别相关对话历史，再通过动态漏失积分-放电机制选择最合适的记忆。在四个中英日语数据集上的实验表明，相比当前最优记忆检索方法，SynapticRAG在多个指标上实现稳定提升，最高达14.66个百分点。本工作连接认知科学与语言模型开发，为对话系统中的记忆管理提供了新范式。
原文摘要 · Abstract (English)
Existing retrieval methods in Large Language Models show degradation in accuracy when handling temporally distributed conversations, primarily due to their reliance on simple similarity-based retrieval. Unlike existing memory retrieval methods that rely solely on semantic similarity, we propose SynapticRAG, which uniquely combines temporal association triggers with biologically-inspired synaptic propagation mechanisms. Our approach uses temporal association triggers and synaptic-like stimulus propagation to identify relevant dialogue histories. A dynamic leaky integrate-and-fire mechanism then selects the most contextually appropriate memories. Experiments on four datasets of English, Chinese and Japanese show that compared to state-of-the-art memory retrieval methods, SynapticRAG achieves consistent improvements across multiple metrics up to 14.66% points. This work bridges the gap between cognitive science and language model development, providing a new framework for memory management in conversational systems.
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。