Automating Knowledge Acquisition for Content-Centric Cognitive Agents Using LLMs
This work addresses the challenge of scaling semantic lexicons for content-centric cognitive agents, though it appears incremental as it builds on existing lexicons and methods.
The paper tackles the problem of automating knowledge acquisition for cognitive agents by using large language models (LLMs) to learn new multiword expressions equivalent to transitive verbs, resulting in a hybrid learning architecture that integrates knowledge-based methods with LLMs and data analytics.
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.