Explaining Sources of Uncertainty in Automated Fact-Checking

TL;DR

This paper introduces CLUE, a framework that explains model uncertainty in fact-checking by identifying conflicting or agreeing evidence spans, improving interpretability and trust.

Contribution

CLUE is the first method to generate natural language explanations of uncertainty by highlighting evidence interactions without requiring fine-tuning.

Findings

CLUE produces more faithful and consistent explanations than baseline prompting.

Human evaluators find CLUE explanations more helpful and logically coherent.

CLUE generalizes to other tasks requiring complex reasoning over evidence.

Abstract

Understanding sources of a model's uncertainty regarding its predictions is crucial for effective human-AI collaboration. Prior work proposes using numerical uncertainty or hedges ("I'm not sure, but ..."), which do not explain uncertainty that arises from conflicting evidence, leaving users unable to resolve disagreements or rely on the output. We introduce CLUE (Conflict-and-Agreement-aware Language-model Uncertainty Explanations), the first framework to generate natural language explanations of model uncertainty by (i) identifying relationships between spans of text that expose claim-evidence or inter-evidence conflicts and agreements that drive the model's predictive uncertainty in an unsupervised way, and (ii) generating explanations via prompting and attention steering that verbalize these critical interactions. Across three language models and two fact-checking datasets, we show that CLUE produces explanations that are more faithful to the model's uncertainty and more consistent with fact-checking decisions than prompting for uncertainty explanations without span-interaction guidance. Human evaluators judge our explanations to be more helpful, more informative, less redundant, and more logically consistent with the input than this baseline. CLUE requires no fine-tuning or architectural changes, making it plug-and-play for any white-box language model. By explicitly linking uncertainty to evidence conflicts, it offers practical support for fact-checking and generalises readily to other tasks that require reasoning over complex information.