Pattern-based Logical Fallacy Classification using Decoder-Only Large Language Models

ACL ARR 2026 January Submission10471 Authors

Keywords: Fallacy Detection, Argumentation Mining, Large Language Models

Abstract:

In today's fast-paced information era, logical fallacies, defined as defective patterns of reasoning, inevitably contribute to the growth of information disorder. However, often fallacies appear in nuanced forms that complicate automated classification. In this study, we investigate whether the logical structure of arguments proves beneficial for fallacy classification by developing a framework that extract logical patterns using Large Language Models (LLMs).
We evaluate the impact of these patterns across different LLMs and experimental zero- and one-shot configurations, showing statistically significant improvements over zero-shot baselines and outperforming competing approaches.
Cross-dataset experiments validate generalization, establishing data-driven pattern extraction as an effective method for generating logical representations.

Paper Type: Long

Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Research Area Keywords: rhetoric and framing, argument schemes and reasoning

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 10471