Multitask Instruction-based Prompting for Fallacy Recognition

Tariq Alhindi, Tuhin Chakrabarty, Elena Musi, Smaranda Muresan


Abstract
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.
Anthology ID:
2022.emnlp-main.560
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8172–8187
Language:
URL:
https://aclanthology.org/2022.emnlp-main.560
DOI:
10.18653/v1/2022.emnlp-main.560
Bibkey:
Cite (ACL):
Tariq Alhindi, Tuhin Chakrabarty, Elena Musi, and Smaranda Muresan. 2022. Multitask Instruction-based Prompting for Fallacy Recognition. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8172–8187, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Multitask Instruction-based Prompting for Fallacy Recognition (Alhindi et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.560.pdf