Enriching Taxonomies Using Large Language Models

TL;DR

This paper introduces Taxoria, a pipeline that uses Large Language Models to enrich existing taxonomies by proposing and validating new nodes, thereby improving coverage and relevance for better knowledge organization.

Contribution

It presents a novel taxonomy enrichment method leveraging LLMs with validation, enhancing existing taxonomies beyond prior extraction-based approaches.

Findings

Enriched taxonomies show increased coverage and relevance.

Validation reduces hallucinations and improves semantic accuracy.

Visualization aids in analyzing the enriched taxonomy structure.

Abstract

Taxonomies play a vital role in structuring and categorizing information across domains. However, many existing taxonomies suffer from limited coverage and outdated or ambiguous nodes, reducing their effectiveness in knowledge retrieval. To address this, we present Taxoria, a novel taxonomy enrichment pipeline that leverages Large Language Models (LLMs) to enhance a given taxonomy. Unlike approaches that extract internal LLM taxonomies, Taxoria uses an existing taxonomy as a seed and prompts an LLM to propose candidate nodes for enrichment. These candidates are then validated to mitigate hallucinations and ensure semantic relevance before integration. The final output includes an enriched taxonomy with provenance tracking and visualization of the final merged taxonomy for analysis.