ClaimCheck: Automatic Fact-Checking of Textual Claims using Web Evidence
Akshith Reddy Putta, Jacob Devasier, Chengkai Li · 2025
We introduce ClaimCheck, an efficient factchecking system that verifies textual claims using smaller, open-source large language models.ClaimCheck integrates two factchecking strategies, claim-matching and novel claim processing.Claim-matching uses related fact-checks from trusted organizations to fact-check a claim.Novel claim processing breaks down fact-checking into manageable subtasks-generating targeted questions, retrieving Web evidence, extracting answers, and synthesizing verdicts.Evaluation on the AVeriTeC benchmark demonstrates 62.6% verdict prediction accuracy, with claim-matching providing a 2.8% improvement.ClaimCheck approaches the performance of state-of-theart systems while requiring significantly fewer computational resources, demonstrating the effectiveness of using small language models for fact-checking tasks.Furthermore, our code is publicly available to help make automated factchecking more accessible.