What type of study is this?

This is a Quantitative Study study.

October 19, 2025

Constructing a Domain‐Specific Taxonomy by Aligning Multiple Large Language Models’ Outputs

EYEthan M. YooRutgers, The State University of New Jersey YCYi‐Yun ChengRutgers, The State University of New Jersey

Key Points

The proposed workflow successfully generates coherent taxonomies using outputs from multiple large language models.
Taxonomies created have a maximum of two levels and 30 nodes, based on prompts given to six state-of-the-art LLMs.
This methodology includes LLM prompting, taxonomy alignment, and human validation to enhance the taxonomy construction process.
Future research will focus on collaborating with domain experts to verify the taxonomies and exploring the workflow's adaptability across different domains.

Abstract

ABSTRACT Taxonomies organize concepts into broad categories consisting of more specific subcategories. In this study, we explore the use of multiple large language models (LLMs) to construct a domain‐specific taxonomy. We propose a five‐step workflow that combines LLM prompting, taxonomy alignment, and human validation. To test this workflow, we prompted six state‐of‐the‐art LLMs to generate taxonomies with a maximum of two levels and 30 nodes. Although there were structural and syntactic variations, all models produced coherent taxonomies. Our findings suggest that even in the absence of ground truth data to facilitate taxonomy construction, integrating outputs from multiple LLMs can result in a reasonable starting point for a domain‐specific taxonomy. In future work, we plan to complete the remaining steps in our proposed workflow by working with domain experts to verify the combined taxonomies; we will also test the generalizability of this workflow to other domains.

Ask AI

Helpful

Bookmark

View Full Paper