Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering

Helena Bonaldi, Greta Damo, Nicolás Ocampo, Elena Cabrio, Serena Villata, Marco Guerini


Abstract
The potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of automatically producing it. However, automatically generated responses often lack the argumentative richness which characterises expert-produced counterspeech. In this work, we focus on two aspects of counterspeech generation to produce more cogent responses. First, by investigating the tension between helpfulness and harmlessness of LLMs, we test whether the presence of safety guardrails hinders the quality of the generations. Secondly, we assess whether attacking a specific component of the hate speech results in a more effective argumentative strategy to fight online hate. By conducting an extensive human and automatic evaluation, we show how the presence of safety guardrails can be detrimental also to a task that inherently aims at fostering positive social interactions. Moreover, our results show that attacking a specific component of the hate speech, and in particular its implicit negative stereotype and its hateful parts, leads to higher-quality generations.
Anthology ID:
2024.emnlp-main.201
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:
3446–3463
Language:
URL:
https://aclanthology.org/2024.emnlp-main.201
DOI:
Bibkey:
Cite (ACL):
Helena Bonaldi, Greta Damo, Nicolás Ocampo, Elena Cabrio, Serena Villata, and Marco Guerini. 2024. Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3446–3463, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering (Bonaldi et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.201.pdf
Data:
 2024.emnlp-main.201.data.zip