PREDICT: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection

Someen Park, Jaehoon Kim, Seungwan Jin, Sohyun Park, Kyungsik Han


Abstract
While a few public benchmarks have been proposed for training hate speech detection models, the differences in labeling criteria between these benchmarks pose challenges for generalized learning, limiting the applicability of the models. Previous research has presented methods to generalize models through data integration or augmentation, but overcoming the differences in labeling criteria between datasets remains a limitation. To address these challenges, we propose PREDICT, a novel framework that uses the notion of multi-agent for hate speech detection. PREDICT consists of two phases: (1) PRE (Perspective-based REasoning): Multiple agents are created based on the induced labeling criteria of given datasets, and each agent generates stances and reasons; (2) DICT (Debate using InCongruenT references): Agents representing hate and non-hate stances conduct the debate, and a judge agent classifies hate or non-hate and provides a balanced reason. Experiments on five representative public benchmarks show that PREDICT achieves superior cross-evaluation performance compared to methods that focus on specific labeling criteria or majority voting methods. Furthermore, we validate that PREDICT effectively mediates differences between agents’ opinions and appropriately incorporates minority opinions to reach a consensus. Our code is available at https://github.com/Hanyang-HCC-Lab/PREDICT
Anthology ID:
2024.emnlp-main.1166
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20963–20987
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1166
DOI:
Bibkey:
Cite (ACL):
Someen Park, Jaehoon Kim, Seungwan Jin, Sohyun Park, and Kyungsik Han. 2024. PREDICT: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20963–20987, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
PREDICT: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection (Park et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1166.pdf