keyword
explainable fake news detection
Explainable fake news detection is the process of using computational systems to identify false or misleading information while providing human-interpretable rationales and evidence to justify the veracity classification. Rather than operating as opaque models that solely assign truth ratings to statements, explainable detection frameworks expose the underlying verification process through mechanisms such as claim decomposition, multi-step reasoning traces, and evidentiary source attribution. By presenting explicit justifications that clarify which specific components of a claim are unsupported, misleading, or factual, these systems help users, fact-checkers, and auditors assess the reliability of the automated verdict and understand the logical steps behind each decision.
2 items
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
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
Generating Literal and Implied Subquestions to Fact-check Complex Claims
Jifan Chen, Aniruddh Sriram, Eunsol Choi, Greg Durrett
Why you should read this
Introduces ClaimDecomp, a benchmark for breaking down complex political claims into literal and implied yes-no subquestions, proving that question decomposition improves evidence retrieval and provides explainable step-by-step veracity judgments.
Verifying political claims is a challenging task, as politicians can use various tactics to subtly misrepresent the facts for their agenda. Existing automatic fact-checking systems fall short here, and their predictions like “half-true” are not very useful in isolation, since it is unclear which parts of a claim are true or false. In this work, we focus on decomposing a complex claim into a comprehensive set of yes-no subquestions whose answers influence the veracity of the claim. We present ClaimDecomp, a dataset of decompositions for over 1000 claims. Given a claim and its verification paragraph written by fact-checkers, our trained annotators write subquestions covering both explicit propositions of the original claim and its implicit facets, such as additional political context that changes our view of the claim’s veracity. We study whether state-of-the-art pre-trained models can learn to generate such subquestions. Our experiments show that these models generate reasonable questions, but predicting implied subquestions based only on the claim (without consulting other evidence) remains challenging. Nevertheless, we show that predicted subquestions can help identify relevant evidence to fact-check the full claim and derive the veracity through their answers, suggesting that claim decomposition can be a useful piece of a fact-checking pipeline.¹
Added
2026-09-26