{"ID":2873540,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06883","arxiv_id":"2509.06883","title":"UNH at CheckThat! 2025: Fine-tuning Vs Prompting in Claim Extraction","abstract":"We participate in CheckThat! Task 2 English and explore various methods of prompting and in-context learning, including few-shot prompting and fine-tuning with different LLM families, with the goal of extracting check-worthy claims from social media passages. Our best METEOR score is achieved by fine-tuning a FLAN-T5 model. However, we observe that higher-quality claims can sometimes be extracted using other methods, even when their METEOR scores are lower.","short_abstract":"We participate in CheckThat! Task 2 English and explore various methods of prompting and in-context learning, including few-shot prompting and fine-tuning with different LLM families, with the goal of extracting check-worthy claims from social media passages. Our best METEOR score is achieved by fine-tuning a FLAN-T5 m...","url_abs":"https://arxiv.org/abs/2509.06883","url_pdf":"https://arxiv.org/pdf/2509.06883v1","authors":"[\"Joe Wilder\",\"Nikhil Kadapala\",\"Benji Xu\",\"Mohammed Alsaadi\",\"Aiden Parsons\",\"Mitchell Rogers\",\"Palash Agarwal\",\"Adam Hassick\",\"Laura Dietz\"]","published":"2025-09-08T17:02:34Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.IR\"]","methods":"[\"Large Language Model\"]","has_code":false}