Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech

Neemesh Yadav, Sarah Masud, Vikram Goyal, Md Shad Akhtar, Tanmoy Chakraborty


Abstract
Employing language models to generate explanations for an incoming implicit hate post is an active area of research. The explanation is intended to make explicit the underlying stereotype and aid content moderators. The training often combines top-k relevant knowledge graph (KG) tuples to provide world knowledge and improve performance on standard metrics. Interestingly, our study presents conflicting evidence for the role of the quality of KG tuples in generating implicit explanations. Consequently, simpler models incorporating external toxicity signals outperform KG-infused models. Compared to the KG-based setup, we observe a comparable performance for SBIC (LatentHatred) datasets with a performance variation of +0.44 (+0.49), +1.83 (-1.56), and -4.59 (+0.77) in BLEU, ROUGE-L, and BERTScore. Further human evaluation and error analysis reveal that our proposed setup produces more precise explanations than zero-shot GPT-3.5, highlighting the intricate nature of the task.
Anthology ID:
2024.findings-acl.831
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13967–13983
Language:
URL:
https://aclanthology.org/2024.findings-acl.831
DOI:
10.18653/v1/2024.findings-acl.831
Bibkey:
Cite (ACL):
Neemesh Yadav, Sarah Masud, Vikram Goyal, Md Shad Akhtar, and Tanmoy Chakraborty. 2024. Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13967–13983, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech (Yadav et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.831.pdf