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

arXiv: https://arxiv.org/abs/2504.00343 · HTML: https://mlsanity.com/paper/2504.00343/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 40 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 7 of 7)

- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts](https://mlsanity.com/paper/2209.14557/) (2022)
- [The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection](https://mlsanity.com/paper/2411.11081/) (2024)
- [SemEval-2020 Task 6: Definition extraction from free text with the DEFT corpus](https://mlsanity.com/paper/2008.13694/) (2020)
- [The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias](https://mlsanity.com/paper/2312.16148/) (2023)
- [An Interdisciplinary Approach for the Automated Detection and Visualization of Media Bias in News Articles](https://mlsanity.com/paper/2112.13352/) (2021)
- [Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning](https://mlsanity.com/paper/2309.14771/) (2023)

## Built on by (most cited first, 2 of 2)

- [SciDef: Datasets and Tools for Automated Definition Extraction from Scientific Literature with LLMs](https://mlsanity.com/paper/2602.05413/) (2026)
- [Definitional Sensitivity in Media Bias Detection: A Multi-Definition Dataset and Benchmark](https://mlsanity.com/paper/2608.23095/) (2026)

## Abstract (arXiv)

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.