# Joint Effects of Argumentation Theory, Audio Modality and Data Enrichment on LLM-Based Fallacy Classification

arXiv: https://arxiv.org/abs/2509.11127 · HTML: https://mlsanity.com/paper/2509.11127/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 3 of its 14 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 3 of 3)

- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [Argotario: Computational Argumentation Meets Serious Games](https://mlsanity.com/paper/1707.06002/) (2017)
- [A Logical Fallacy-Informed Framework for Argument Generation](https://mlsanity.com/paper/2408.03618/) (2024)

## Built on by (most cited first, 1 of 1)

- [Evaluating VLMs on Multimodal Aristotelian Persuasion Tasks](https://mlsanity.com/paper/2608.01238/) (2026)

## Abstract (arXiv)

This study investigates how context and emotional tone metadata influence large language model (LLM) reasoning and performance in fallacy classification tasks, particularly within political debate settings. Using data from U.S. presidential debates, we classify six fallacy types through various prompting strategies applied to the Qwen-3 (8B) model. We introduce two theoretically grounded Chain-of-Thought frameworks: Pragma-Dialectics and the Periodic Table of Arguments, and evaluate their effectiveness against a baseline prompt under three input settings: text-only, text with context, and text with both context and audio-based emotional tone metadata. Results suggest that while theoretical prompting can improve interpretability and, in some cases, accuracy, the addition of context and especially emotional tone metadata often leads to lowered performance. Emotional tone metadata biases the model toward labeling statements as textitAppeal to Emotion, worsening logical reasoning. Overall, basic prompts often outperformed enhanced ones, suggesting that attention dilution from added inputs may worsen rather than improve fallacy classification in LLMs.