Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

fact-checking complex claims

Fact-checking complex claims refers to the systematic verification of real-world statements that cannot be validated by a single piece of evidence and instead require multi-step reasoning across multiple sources. Unlike simple fact-checking, which confirms straightforward, atomic assertions through direct lookups, evaluating complex claims involves decomposing multifaceted statements into simpler sub-tasks or intermediate questions. These sub-tasks are then addressed through targeted information retrieval and logical, numerical, or contextual analysis before the resulting evidence is synthesized to determine the overall veracity of the claim and generate an interpretable explanation of the verification process.

1 item

Fact-Checking Complex Claims with Program-Guided Reasoning

Fact-Checking Complex Claims with Program-Guided Reasoning

Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov

OrganizationsMohamed bin Zayed University of Artificial IntelligenceNanyang Technological UniversityNational University of SingaporeUniversity of California, Santa Barbara

Why you should read this

Proposes a program-guided framework that decomposes complex claims into executable reasoning steps handled by specialized tools, delivering interpretable and data-efficient automated fact-checking that outperforms competitive baselines across multiple evidence settings.

Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning. In this paper, we present Program-Guided Fact-Checking (PROGRAMFC), a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions. We first leverage the in-context learning ability of large language models to generate reasoning programs to guide the verification process. Afterward, we execute the program by delegating each sub-task to the corresponding sub-task handler. This process makes our model both explanatory and data-efficient, providing clear explanations of its reasoning process and requiring minimal training data. We evaluate PROGRAMFC on two challenging fact-checking datasets and show that it outperforms seven fact-checking baselines across different settings of evidence availability, with explicit output programs that benefit human debugging.1

Added

2026-09-28