Larimar: Large Language Models with Episodic Memory Control

arXiv:2403.11901v1 Announce Type: new
Abstract: Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episodic memory. Larimar's memory allows for dynamic, one-shot updates of knowledge without the need for computationally expensive re-training or fine-tuning. Experimental results on multiple fact editing benchmarks demonstrate that Larimar attains accuracy comparable to most competitive baselines, even in …

abstract architecture arxiv brain brain-inspired challenges control cs.ai cs.lg distributed dynamic knowledge language language models large language large language models llms memory novel paper research type updates