CLAIIRSep 8, 2025

UNH at CheckThat! 2025: Fine-tuning Vs Prompting in Claim Extraction

arXiv:2509.06883v1h-index: 2CLEF
Originality Synthesis-oriented
AI Analysis

This work addresses claim extraction for fact-checking, but it is incremental as it compares existing techniques without introducing new methods.

The paper tackled claim extraction from social media by comparing fine-tuning and prompting methods, achieving a best METEOR score with fine-tuned FLAN-T5 but noting that other methods sometimes yield higher-quality claims despite lower scores.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes