RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models

TL;DR

RecallM introduces an adaptable long-term memory system for Large Language Models, enhancing belief updating and temporal understanding, which improves knowledge management and reasoning capabilities beyond existing methods.

Contribution

The paper presents RecallM, a novel memory architecture that significantly improves belief updating and temporal understanding in LLMs, surpassing vector database methods.

Findings

RecallM is four times more effective than vector databases for belief updating.

RecallM achieves competitive results on question-answering and in-context learning tasks.

The architecture enhances long-term knowledge management in LLMs.

Abstract

Large Language Models (LLMs) have made extraordinary progress in the field of Artificial Intelligence and have demonstrated remarkable capabilities across a large variety of tasks and domains. However, as we venture closer to creating Artificial General Intelligence (AGI) systems, we recognize the need to supplement LLMs with long-term memory to overcome the context window limitation and more importantly, to create a foundation for sustained reasoning, cumulative learning and long-term user interaction. In this paper we propose RecallM, a novel architecture for providing LLMs with an adaptable and updatable long-term memory mechanism. Unlike previous methods, the RecallM architecture is particularly effective at belief updating and maintaining a temporal understanding of the knowledge provided to it. We demonstrate through various experiments the effectiveness of this architecture. Furthermore, through our own temporal understanding and belief updating experiments, we show that RecallM is four times more effective than using a vector database for updating knowledge previously stored in long-term memory. We also demonstrate that RecallM shows competitive performance on general question-answering and in-context learning tasks.