SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms
Yuki Hou, Haruki Tamoto, Qinghua Zhao, Homei Miyashita · 2025
Existing retrieval methods in Large LanguageModels 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-andfire 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. 1