Complex Claim Verification with Evidence Retrieved in the Wild
This addresses the challenge of real-time fact-checking for emerging claims, potentially assisting human fact-checkers, though it is incremental as it builds on prior evidence retrieval methods.
The authors tackled the problem of verifying complex political claims by developing the first fully automated pipeline that retrieves raw evidence from the web, restricted to documents available before the claim was made, and showed that aggregated evidence improves veracity judgments.
Evidence retrieval is a core part of automatic fact-checking. Prior work makes simplifying assumptions in retrieval that depart from real-world use cases: either no access to evidence, access to evidence curated by a human fact-checker, or access to evidence available long after the claim has been made. In this work, we present the first fully automated pipeline to check real-world claims by retrieving raw evidence from the web. We restrict our retriever to only search documents available prior to the claim's making, modeling the realistic scenario where an emerging claim needs to be checked. Our pipeline includes five components: claim decomposition, raw document retrieval, fine-grained evidence retrieval, claim-focused summarization, and veracity judgment. We conduct experiments on complex political claims in the ClaimDecomp dataset and show that the aggregated evidence produced by our pipeline improves veracity judgments. Human evaluation finds the evidence summary produced by our system is reliable (it does not hallucinate information) and relevant to answering key questions about a claim, suggesting that it can assist fact-checkers even when it cannot surface a complete evidence set.