Enriching Taxonomies Using Large Language Models

Researchers have developed Taxoria, a new taxonomy enrichment pipeline that uses Large Language Models to enhance existing taxonomies by proposing, validating, and integrating new nodes. The system addresses limitations in current taxonomies such as limited coverage and outdated information while including hallucination mitigation and provenance tracking.

• →Taxoria leverages LLMs to automatically enrich existing taxonomies rather than extracting internal LLM taxonomies.
• →The system includes validation mechanisms to prevent AI hallucinations and ensure semantic relevance of new taxonomy nodes.
• →The pipeline provides provenance tracking and visualization capabilities for analyzing the enriched taxonomy.
• →This approach addresses common taxonomy issues including limited coverage and outdated categorization structures.
• →The research represents advancement in using AI to improve knowledge organization and information retrieval systems.