Detecting argumentative fallacies in the wild: Problems and limitations of large language models

F Pan, X Wu, Z Li, AT Luu - arXiv preprint arXiv:2410.15050, 2024 - arxiv.org

Fallacies are defective arguments with faulty reasoning. Detecting and classifying them is a
crucial NLP task to prevent misinformation, manipulative claims, and biased decisions …

被引用次数：5 相关文章所有 3 个版本

[PDF] arxiv.org

Can Large Language Models perform Relation-based Argument Mining?

D Gorur, A Rago, F Toni - arXiv preprint arXiv:2402.11243, 2024 - arxiv.org

Argument mining (AM) is the process of automatically extracting arguments, their
components and/or relations amongst arguments and components from text. As the number …

被引用次数：4 相关文章所有 2 个版本

[PDF] arxiv.org

A Few Hypocrites: Few-Shot Learning and Subtype Definitions for Detecting Hypocrisy Accusations in Online Climate Change Debates

PG Corral, A Green, H Meyer, A Stoll, X Yan… - arXiv preprint arXiv …, 2024 - arxiv.org

The climate crisis is a salient issue in online discussions, and hypocrisy accusations are a
central rhetorical element in these debates. However, for large-scale text analysis, hypocrisy …

Critical Questions Generation: Motivation and Challenges

BC Figueras, R Agerri - arXiv preprint arXiv:2410.14335, 2024 - arxiv.org

The development of Large Language Models (LLMs) has brought impressive performances
on mitigation strategies against misinformation, such as counterargument generation …

Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling

I Robbani, P Reisert, N Inoue, S Pothong… - arXiv preprint arXiv …, 2024 - arxiv.org

Prior research in computational argumentation has mainly focused on scoring the quality of
arguments, with less attention on explicating logical errors. In this work, we introduce four …

[PDF] arxiv.org