Automating Knowledge Acquisition for Content-Centric Cognitive Agents Using LLMs

TL;DR

This paper presents a hybrid system that leverages large language models to automatically expand an agent's semantic lexicon, improving knowledge acquisition through a combination of formal representations, natural language generation, and quality control.

Contribution

It introduces a novel hybrid learning architecture that combines knowledge-based methods with LLMs for automatic lexicon expansion in cognitive agents.

Findings

Effective learning of multiword expressions with LLMs

Hybrid architecture improves knowledge acquisition accuracy

Demonstrates benefits of combining formal methods with LLMs

Abstract

The paper describes a system that uses large language model (LLM) technology to support the automatic learning of new entries in an intelligent agent's semantic lexicon. The process is bootstrapped by an existing non-toy lexicon and a natural language generator that converts formal, ontologically-grounded representations of meaning into natural language sentences. The learning method involves a sequence of LLM requests and includes an automatic quality control step. To date, this learning method has been applied to learning multiword expressions whose meanings are equivalent to those of transitive verbs in the agent's lexicon. The experiment demonstrates the benefits of a hybrid learning architecture that integrates knowledge-based methods and resources with both traditional data analytics and LLMs.