Exploiting Language Models as a Source of Knowledge for Cognitive Agents

TL;DR

This paper explores how large language models can serve as external knowledge sources for cognitive agents, addressing challenges and proposing integration methods to enhance knowledge extraction within cognitive architectures.

Contribution

It introduces a framework for integrating language models with cognitive architectures to improve knowledge extraction for cognitive agents.

Findings

Identified key challenges in using LLMs as knowledge sources.

Proposed methods for integrating LLMs with cognitive architectures.

Demonstrated improved knowledge extraction through integration examples.

Abstract

Large language models (LLMs) provide capabilities far beyond sentence completion, including question answering, summarization, and natural-language inference. While many of these capabilities have potential application to cognitive systems, our research is exploiting language models as a source of task knowledge for cognitive agents, that is, agents realized via a cognitive architecture. We identify challenges and opportunities for using language models as an external knowledge source for cognitive systems and possible ways to improve the effectiveness of knowledge extraction by integrating extraction with cognitive architecture capabilities, highlighting with examples from our recent work in this area.