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.
@article{arxiv.2504.00343,
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},
journal= {arXiv preprint arXiv:2504.00343},
year = {2025}
}