CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking
This addresses a gap in fact-checking models for claims needing external context, but it is incremental as it builds on existing reasoning methods by adding context and reference layers.
The paper tackles the problem of fact-checking claims that require understanding evidence sentences with incomplete information, such as coreferences and acronyms, by proposing a method that integrates auxiliary contexts and references into a three-layer evidence graph and evidence-conditioned prompts. The result is a model that shows verified strength in experiments, though no specific numbers are provided.
Fact-checking the truthfulness of claims usually requires reasoning over multiple evidence sentences. Oftentimes, evidence sentences may not be always self-contained, and may require additional contexts and references from elsewhere to understand coreferential expressions, acronyms, and the scope of a reported finding. For example, evidence sentences from an academic paper may need contextual sentences in the paper and descriptions in its cited papers to determine the scope of a research discovery. However, most fact-checking models mainly focus on the reasoning within evidence sentences, and ignore the auxiliary contexts and references. To address this problem, we propose a novel method, Context- and Reference-augmented Reasoning and Prompting. For evidence reasoning, we construct a three-layer evidence graph with evidence, context, and reference layers. We design intra- and cross-layer reasoning to integrate three graph layers into a unified evidence embedding. For verdict prediction, we design evidence-conditioned prompt encoder, which produces unique prompt embeddings for each claim. These evidence-conditioned prompt embeddings and claims are unified for fact-checking. Experiments verify the strength of our model.