Show me the evidence: Evaluating the role of evidence and natural language explanations in AI-supported fact-checking
Greta Warren, Jingyi Sun, Irina Shklovski, Isabelle Augenstein
TL;DR
The paper addresses how evidence and natural language explanations affect AI-assisted fact-checking by non-experts. It uses a rigorous mixed-methods 3x2x2 design to compare uncertainty-based explanations, verdict explanations, and no explanations while providing in-window evidence, across eight claims. Key findings show that evidence is the most influential information source, explanations add value especially when AI predictions are correct, and trust modulates how people use explanations versus evidence. The results emphasize the practical importance of making underlying evidence easily accessible and hint at design principles to mitigate overreliance in AI-supported information-seeking systems.
Abstract
Although much research has focused on AI explanations to support decisions in complex information-seeking tasks such as fact-checking, the role of evidence is surprisingly under-researched. In our study, we systematically varied explanation type, AI prediction certainty, and correctness of AI system advice for non-expert participants, who evaluated the veracity of claims and AI system predictions. Participants were provided the option of easily inspecting the underlying evidence. We found that participants consistently relied on evidence to validate AI claims across all experimental conditions. When participants were presented with natural language explanations, evidence was used less frequently although they relied on it when these explanations seemed insufficient or flawed. Qualitative data suggests that participants attempted to infer evidence source reliability, despite source identities being deliberately omitted. Our results demonstrate that evidence is a key ingredient in how people evaluate the reliability of information presented by an AI system and, in combination with natural language explanations, offers valuable support for decision-making. Further research is urgently needed to understand how evidence ought to be presented and how people engage with it in practice.