Benchmarking Check-Worthiness Models on LLM Generated Claims

Charlie George Roadhouse, Matthew Shardlow, Ashley Williams


Abstract
The proliferation of large language models (LLMs) has significantly increased the potential for automated dissemination of disinformation, necessitating robust systems for check-worthiness detection. However, existing models are primarily trained on human claims, leaving their performance on machine-generated text largely unexplored. In this paper, we benchmark encoder models (BERT and RoBERTa) and industry accessible tools (ClaimBuster) against LLM-paraphrased claims across three stylistic categories: syntactic restructuring, syntactic complexity and lexical informality. Our results indicate a consistent performance degradation on synthetic claims, particularly on complex and informal claims. We demonstrate that adversarial training significantly improves model resilience, with RoBERTa achieving F1-score gains up to +5.22 on the CheckIt dataset. Finally, SHAP analysis reveals that while base models rely on narrow syntactic heuristics such as active voice, robust models learn to anchor their prediction on core factual entities. These findings highlight the necessity of stylistic-aware training to maintain fact-checking efficacy in an increasingly LLM-populated information landscape.
Anthology ID:
2026.indor-1.4
Volume:
Proceedings of the 1st Workshop on Information Disorder (InDor) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Simona Frenda, Marco Antonio Stranisci, Shaina Ashraf, Ada Ren, Ioannis Konstas, Usman Naseem
Venues:
InDor | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
34–44
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-indor-04
DOI:
10.63317/5c8w857kxgsn
Bibkey:
Cite (ACL):
Charlie George Roadhouse, Matthew Shardlow, and Ashley Williams. 2026. Benchmarking Check-Worthiness Models on LLM Generated Claims. In Proceedings of the 1st Workshop on Information Disorder (InDor) @ LREC 2026, pages 34–44, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).
Cite (Informal):
Benchmarking Check-Worthiness Models on LLM Generated Claims (Roadhouse et al., InDor 2026)
Copy Citation: