@inproceedings{spinde_leveraging_2025,

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},

url = {https://github.com/Media-Bias-Group/Taxomatic},

year  = {2025},

date = {2025-06-01},

urldate = {2025-06-01},

booktitle = {Proceedings of the International AAAI Conference on Web and Social Media (ICWSM'25)},

volume = {19},

publisher = {AAAI},

address = {Copenhagen, Denmark},

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 framework’s 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.},

keywords = {definition extraction, LLM, media bias, relevance classification, taxonomy building},

pubstate = {published},

tppubtype = {inproceedings}

}