Reconstructing Fallacies in Misrepresented Science and Argument Mining in the Wild

Abstract

In this talk, I will discuss our recent work on applying and investigating language model (LM)-based argument mining technologies in real-world scenarios, including fact-checking misinformation that misrepresents scientific publications and tackling traditional argument mining tasks in various out-of-distribution (OOD) scenarios. First, I will discuss our work on reconstructing and grounding fallacies in misrepresented science, in which health-related misinformation claims often falsely cite a credible biomedical publication as evidence. I will present a new argumentation theoretical model for fallacious reasoning, together with a new dataset for real-world misinformation detection that misrepresents biomedical publications. In the second part of the talk, I will discuss our findings on LMs' capabilities for three OOD scenarios (topic shift, domain shift, and language shift) across eleven argument mining tasks.