Grounding Fallacies Misrepresenting Scientific Publications in Evidence

TL;DR

This paper introduces MissciPlus, a dataset for detecting and explaining logical fallacies in misrepresented scientific publications, to improve fact-checking and misinformation detection in health-related claims.

Contribution

MissciPlus extends previous datasets by grounding fallacies in real scientific passages, enabling realistic evaluation of retrieval, explanation, and fact-checking models.

Findings

Fact-checking models struggle with misrepresented scientific evidence.

Large language models can be misled into accepting false claims.

The dataset enables benchmarking of fallacy detection and explanation methods.

Abstract

Health-related misinformation claims often falsely cite a credible biomedical publication as evidence. These publications only superficially seem to support the false claim, when logical fallacies are applied. In this work, we aim to detect and to highlight such fallacies, which requires assessing the exact content of the misrepresented publications. To achieve this, we introduce MissciPlus, an extension of the fallacy detection dataset Missci. MissciPlus extends Missci by grounding the applied fallacies in real-world passages from misrepresented studies. This creates a realistic test-bed for detecting and verbalizing fallacies under real-world input conditions, and enables new and realistic passage-retrieval tasks. MissciPlus is the first logical fallacy dataset which pairs the real-world misrepresented evidence with incorrect claims, identical to the input to evidence-based fact-checking models. With MissciPlus, we i) benchmark retrieval models in identifying passages that support claims only with fallacious reasoning, ii) evaluate how well LLMs verbalize fallacious reasoning based on misrepresented scientific passages, and iii) assess the effectiveness of fact-checking models in refuting claims that misrepresent biomedical research. Our findings show that current fact-checking models struggle to use misrepresented scientific passages to refute misinformation. Moreover, these passages can mislead LLMs into accepting false claims as true.