Leveraging Large Language Models for Automated Definition Extraction with TaxoMatic A Case Study on Media Bias

Timo Spinde, Luyang Lin, Smi Hinterreiter, Isao Echizen
4/1/2025
cs.CL

No official code found. Best implementation: Media-Bias-Group/Taxomatic (0 stars, last commit 2026-01-23).

Abstract

This paper introduces TaxoMatic, a framework that leverages large language models to automate definition extraction from academic literature. Focusing on the media bias domain, the framework encompasses data collection, LLM-based relevance classification, and extraction of conceptual definitions. Evaluated on a dataset of 2,398 manually rated articles, the study demonstrates the frameworks effectiveness, with Claude-3-sonnet achieving the best results in both relevance classification and definition extraction. Future directions include expanding datasets and applying TaxoMatic to additional domains.

View on arXivView PDF

Code Implementations(1)

Media-Bias-Group/TaxomaticCommunity77%

Leveraging Large Language Models for Automated Definition Extraction with TaxoMatic - a Case Study on Media Bias

01Jupyter NotebookJan 12, 20259 months agoNOASSERTION

Similar Papers

SciDef: Automating Definition Extraction from Academic Literature with Large Language Models

83% match2 repos72026

The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection

82% match1 repo32024

TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora

79% match1 repo472025

Complementary Learning Approach for Text Classification using Large Language Models

79% match2025

TaxoAlign: Scholarly Taxonomy Generation Using Language Models

78% match1 repo22025

Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis

78% match1 repo2024

Cite this paper

@article{spinde2025leveraging,
  title  = {Leveraging Large Language Models for Automated Definition Extraction with TaxoMatic A Case Study on Media Bias},
  author = {Timo Spinde and Luyang Lin and Smi Hinterreiter and Isao Echizen},
  year   = {2025},
  eprint = {2504.00343},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.00343v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.00343.svg)](https://codeofpaper.com/paper/2504.00343)

Discussion