A Case-Based Persistent Memory for a Large Language Model

TL;DR

This paper advocates integrating case-based reasoning with recent deep learning advances to create persistent memory for large language models, potentially advancing towards Artificial General Intelligence.

Contribution

It highlights the overlooked potential of combining CBR with LLMs and deep learning to develop persistent memory systems for AI.

Findings

CBR can synergize with deep learning and LLMs

Persistent memory could enhance LLM capabilities

Potential step towards Artificial General Intelligence

Abstract

Case-based reasoning (CBR) as a methodology for problem-solving can use any appropriate computational technique. This position paper argues that CBR researchers have somewhat overlooked recent developments in deep learning and large language models (LLMs). The underlying technical developments that have enabled the recent breakthroughs in AI have strong synergies with CBR and could be used to provide a persistent memory for LLMs to make progress towards Artificial General Intelligence.