Leveraging Large Language Models for Automated Definition Extraction with TaxoMatic A Case Study on Media Bias
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912302297513984 |
|---|---|
| author | Spinde, Timo Lin, Luyang Hinterreiter, Smi Echizen, Isao |
| author_facet | Spinde, Timo Lin, Luyang Hinterreiter, Smi Echizen, Isao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00343 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models for Automated Definition Extraction with TaxoMatic A Case Study on Media Bias Spinde, Timo Lin, Luyang Hinterreiter, Smi Echizen, Isao Computation and Language 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. |
| title | Leveraging Large Language Models for Automated Definition Extraction with TaxoMatic A Case Study on Media Bias |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.00343 |