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.
@article{arxiv.2410.13553,
title = {SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms},
author = {Yuki Hou and Haruki Tamoto and Qinghua Zhao and Homei Miyashita},
journal= {arXiv preprint arXiv:2410.13553},
year = {2025}
}