FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text
This addresses the need for more transparent and trustworthy verification tools for consumers of AI-generated content, though it appears incremental by building on existing binary or regression-based approaches.
The paper tackles the problem of verifying factual accuracy in machine-generated text by developing an interactive tool that provides transparency and diverse evidence, enabling users to break down and assess individual claims with explanations and source attributions.
With the widespread consumption of AI-generated content, there has been an increased focus on developing automated tools to verify the factual accuracy of such content. However, prior research and tools developed for fact verification treat it as a binary classification or a linear regression problem. Although this is a useful mechanism as part of automatic guardrails in systems, we argue that such tools lack transparency in the prediction reasoning and diversity in source evidence to provide a trustworthy user experience. We develop Facts&Evidence - an interactive and transparent tool for user-driven verification of complex text. The tool facilitates the intricate decision-making involved in fact-verification, presenting its users a breakdown of complex input texts to visualize the credibility of individual claims along with an explanation of model decisions and attribution to multiple, diverse evidence sources. Facts&Evidence aims to empower consumers of machine-generated text and give them agency to understand, verify, selectively trust and use such text.