# Multitask Instruction-based Prompting for Fallacy Recognition

arXiv: https://arxiv.org/abs/2301.09992 · HTML: https://mlsanity.com/paper/2301.09992/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 24 Jan 2023.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019)
- [SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles](https://mlsanity.com/paper/2009.02696/) (2020)
- [UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training](https://mlsanity.com/paper/2202.12359/) (2022)
- [Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation](https://mlsanity.com/paper/1802.06613/) (2018)
- [Argotario: Computational Argumentation Meets Serious Games](https://mlsanity.com/paper/1707.06002/) (2017)
- [Logical Fallacy Detection](https://mlsanity.com/paper/2202.13758/) (2022)
- [Findings of the NLP4IF-2019 Shared Task on Fine-Grained Propaganda Detection](https://mlsanity.com/paper/1910.09982/) (2019)
- [ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them](https://mlsanity.com/paper/2005.07934/) (2020)
- [aschern at SemEval-2020 Task 11: It Takes Three to Tango: RoBERTa, CRF, and Transfer Learning](https://mlsanity.com/paper/2008.02837/) (2020)
- [Fine-Tuned Neural Models for Propaganda Detection at the Sentence and Fragment levels](https://mlsanity.com/paper/1910.09702/) (2019)

## Built on by (most cited first, 23 of 23)

- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [Large Language Models for Propaganda Span Annotation](https://mlsanity.com/paper/2311.09812/) (2023)
- [Missci: Reconstructing Fallacies in Misrepresented Science](https://mlsanity.com/paper/2406.03181/) (2024)
- [Are LLMs Good Zero-Shot Fallacy Classifiers?](https://mlsanity.com/paper/2410.15050/) (2024)
- [CoCoLoFa: A Dataset of News Comments with Common Logical Fallacies Written by LLM-Assisted Crowds](https://mlsanity.com/paper/2410.03457/) (2024)
- [Fine-grained Fallacy Detection with Human Label Variation](https://mlsanity.com/paper/2502.13853/) (2025)
- [Discourse Structures Guided Fine-grained Propaganda Identification](https://mlsanity.com/paper/2310.18544/) (2023)
- [Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition](https://mlsanity.com/paper/2311.09552/) (2023)
- [Towards a Perspectivist Turn in Argument Quality Assessment](https://mlsanity.com/paper/2502.14501/) (2025)
- [MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification](https://mlsanity.com/paper/2311.09761/) (2023)
- [CASA: Causality-driven Argument Sufficiency Assessment](https://mlsanity.com/paper/2401.05249/) (2024)
- [Augmented CARDS: A machine learning approach to identifying triggers of climate change misinformation on Twitter](https://mlsanity.com/paper/2404.15673/) (2024)
- [An Explainable Framework for Misinformation Identification via Critical Question Answering](https://mlsanity.com/paper/2503.14626/) (2025)
- [Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling](https://mlsanity.com/paper/2406.12402/) (2024)
- [Critical Questions Generation: Motivation and Challenges](https://mlsanity.com/paper/2410.14335/) (2024)
- [Modeling Appropriate Language in Argumentation](https://mlsanity.com/paper/2305.14935/) (2023)
- [Detecting Fallacies in Climate Misinformation: A Technocognitive Approach to Identifying Misleading Argumentation](https://mlsanity.com/paper/2405.08254/) (2024)
- [Investigating Persuasion Techniques in Arabic: An Empirical Study Leveraging Large Language Models](https://mlsanity.com/paper/2405.12884/) (2024)
- [Generative Debunking of Climate Misinformation](https://mlsanity.com/paper/2407.05599/) (2024)
- [Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognition](https://mlsanity.com/paper/2409.13716/) (2024)
- [A Few Hypocrites: Few-Shot Learning and Subtype Definitions for Detecting Hypocrisy Accusations in Online Climate Change Debates](https://mlsanity.com/paper/2409.16807/) (2024)
- [Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate Analysis](https://mlsanity.com/paper/2608.27471/) (2026)
- [UZHCL_for_the_win at Touche: Encoder Fine-Tuning, Synthetic Augmentation, and an Underpowered Encoder-LLM Comparison](https://mlsanity.com/paper/2610.17077/) (2026)

## Abstract (arXiv)

Fallacies are used as seemingly valid arguments to support a position and persuade the audience about its validity. Recognizing fallacies is an intrinsically difficult task both for humans and machines. Moreover, a big challenge for computational models lies in the fact that fallacies are formulated differently across the datasets with differences in the input format (e.g., question-answer pair, sentence with fallacy fragment), genre (e.g., social media, dialogue, news), as well as types and number of fallacies (from 5 to 18 types per dataset). To move towards solving the fallacy recognition task, we approach these differences across datasets as multiple tasks and show how instruction-based prompting in a multitask setup based on the T5 model improves the results against approaches built for a specific dataset such as T5, BERT or GPT-3. We show the ability of this multitask prompting approach to recognize 28 unique fallacies across domains and genres and study the effect of model size and prompt choice by analyzing the per-class (i.e., fallacy type) results. Finally, we analyze the effect of annotation quality on model performance, and the feasibility of complementing this approach with external knowledge.