TL;DR
This paper introduces a method for generating counterfactual explanations for fake news detection, aiming to improve public understanding of why news is classified as fake by leveraging question answering and contradiction detection.
Contribution
It proposes a novel approach to generate counterfactual explanations for fake news using contradiction reasoning and question answering, enhancing interpretability of fact checking systems.
Findings
Outperforms state-of-the-art explanation methods
Generates helpful explanations for fake news detection
Improves user understanding of fact checking predictions
Abstract
Automated fact checking systems have been proposed that quickly provide veracity prediction at scale to mitigate the negative influence of fake news on people and on public opinion. However, most studies focus on veracity classifiers of those systems, which merely predict the truthfulness of news articles. We posit that effective fact checking also relies on people's understanding of the predictions. In this paper, we propose elucidating fact checking predictions using counterfactual explanations to help people understand why a specific piece of news was identified as fake. In this work, generating counterfactual explanations for fake news involves three steps: asking good questions, finding contradictions, and reasoning appropriately. We frame this research question as contradicted entailment reasoning through question answering (QA). We first ask questions towards the false claim and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
