A Case-Based Persistent Memory for a Large Language Model
This is a position paper suggesting a conceptual synergy for AI researchers, but it is incremental as it builds on existing ideas without new results.
The paper argues that case-based reasoning (CBR) researchers have overlooked deep learning and large language models (LLMs), proposing that CBR could provide a persistent memory for LLMs to advance towards Artificial General Intelligence.
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.