An Explainable Framework for Misinformation Identification via Critical Question Answering

2025-03-18

AI Summary

Existing error detection methods predominantly adopt black-box sequence classification, lacking interpretable discrimination between factual inaccuracies and logical fallacies. This paper introduces the first explainable misbelief identification framework integrating argumentation pattern theory with Critical Questions (CQs), jointly modeling classification and question-answering to simultaneously detect factual deviations and inferential flaws while generating natural-language,质疑-style explanations. Key contributions include: (1) establishing an argumentation-structure-based explainable paradigm; (2) releasing NLAS-CQ, the first large-scale corpus of natural-language argumentation with CQs (3,566 argument instances and 4,687 annotated CQ answers); and (3) achieving statistically significant improvements over black-box baselines across multiple metrics—demonstrating both high accuracy and strong interpretability, thereby enhancing user trust and system transparency.

Technology Category

Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)Knowledge Representation and Reasoning: ArgumentationCognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingUser Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systemsSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Natural language misinformation detection approaches have been, to date, largely dependent on sequence classification methods, producing opaque systems in which the reasons behind classification as misinformation are unclear. While an effort has been made in the area of automated fact-checking to propose explainable approaches to the problem, this is not the case for automated reason-checking systems. In this paper, we propose a new explainable framework for both factual and rational misinformation detection based on the theory of Argumentation Schemes and Critical Questions. For that purpose, we create and release NLAS-CQ, the first corpus combining 3,566 textbook-like natural language argumentation scheme instances and 4,687 corresponding answers to critical questions related to these arguments. On the basis of this corpus, we implement and validate our new framework which combines classification with question answering to analyse arguments in search of misinformation, and provides the explanations in form of critical questions to the human user.

Problem

• Develops explainable framework for misinformation detection
• Addresses opacity in sequence classification methods
• Introduces NLAS-CQ corpus for argument analysis

Innovation

• Explainable framework for misinformation detection
• Combines classification with critical question answering
• Uses Argumentation Schemes and Critical Questions theory