mlsanityData to 14 Oct 2026

Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM-based Manipulation Checks

arXiv 2503.00024 ↗First posted 24 Feb 2025cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Emotions have been shown to play a role in argument convincingness, yet this aspect is underexplored in the natural language processing (NLP) community. Unlike prior studies that use static analyses, focus on a single text domain or language, or treat emotion as just one of many factors, we introduce a dynamic framework inspired by manipulation checks commonly used in psychology and social science; leveraging LLM-based manipulation checks, this framework examines the extent to which perceived emotional intensity influences perceived convincingness. Through human evaluation of arguments across different languages, text domains, and topics, we find that in over half of cases, human judgments of convincingness remain unchanged despite variations in perceived emotional intensity; when emotions do have an impact, they more often enhance rather than weaken convincingness. We further analyze whether 11 LLMs behave like humans in the same scenario, finding that while LLMs generally mirror human patterns, they struggle to capture nuanced emotional effects in individual judgments.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 23 of its 55 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

23 of 55 references.

References · 23

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  3. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 723
  4. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  5. 2020Deep Learning for Text Style Transfer: A Surveycited by 162
  6. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  7. 2022Thinking Fast and Slow in Large Language Modelscited by 137
  8. 2024Cognitive Bias in Decision-Making with LLMscited by 106
  9. 2024What Evidence Do Language Models Find Convincing?cited by 75
  10. 2016Argumentation Mining in User-Generated Web Discoursecited by 69
  11. 2023Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Biascited by 53
  12. 2019Automatic Argument Quality Assessment -- New Datasets and Methodscited by 47
11 more
  1. 2017Neural End-to-End Learning for Computational Argumentation Miningcited by 41
  2. 2017Argument Strength is in the Eye of the Beholder: Audience Effects in Persuasioncited by 35
  3. 2019Are You Convinced? Choosing the More Convincing Evidence with a Siamese Networkcited by 29
  4. 2024Are Large Language Models Reliable Argument Quality Annotators?cited by 24
  5. 2024Cognitive Biases in Large Language Models: A Survey and Mitigation Experimentscited by 20
  6. 2021Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biasescited by 13
  7. 2024Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understandingcited by 12
  8. 2024Fearful Falcons and Angry Llamas: Emotion Category Annotations of Arguments by Humans and LLMscited by 11
  9. 2024A Logical Fallacy-Informed Framework for Argument Generationcited by 7
  10. 2022Fine-Grained Detection of Solidarity for Women and Migrants in 155 Years of German Parliamentary Debatescited by 6
  11. 2024Can Factual Statements be Deceptive? The DeFaBel Corpus of Belief-based Deceptioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Large Language Models in Argument Mining: A Surveycited by 14
  2. 2025Emotionally Charged, Logically Blurred: AI-driven Emotional Framing Impairs Human Fallacy Detectioncited by 3
  3. 2025Trust Me, I Can Convince You: The Contextualized Argument Appraisal Frameworkcited by 2
  4. 2025Evaluating Apple Intelligence's Writing Tools for Privacy Against Large Language Model-Based Inference Attacks: Insights from Early Datasetscited by 0
  5. 2025Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?cited by 0
  6. 2026An LLM-Based System for Argument Miningcited by 0