Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse

Rongchen Guo, Isar Nejadgholi, Hillary Dawkins, Kathleen Fraser, Svetlana Kiritchenko


Abstract
This work provides an explanatory view of how LLMs can apply moral reasoning to both criticize and defend sexist language. We assessed eight large language models, all of which demonstrated the capability to provide explanations grounded in varying moral perspectives for both critiquing and endorsing views that reflect sexist assumptions. With both human and automatic evaluation, we show that all eight models produce comprehensible and contextually relevant text, which is helpful in understanding diverse views on how sexism is perceived. Also, through analysis of moral foundations cited by LLMs in their arguments, we uncover the diverse ideological perspectives in models’ outputs, with some models aligning more with progressive or conservative views on gender roles and sexism.Based on our observations, we caution against the potential misuse of LLMs to justify sexist language. We also highlight that LLMs can serve as tools for understanding the roots of sexist beliefs and designing well-informed interventions. Given this dual capacity, it is crucial to monitor LLMs and design safety mechanisms for their use in applications that involve sensitive societal topics, such as sexism.
Anthology ID:
2024.emnlp-main.1090
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:
19548–19564
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1090
DOI:
Bibkey:
Cite (ACL):
Rongchen Guo, Isar Nejadgholi, Hillary Dawkins, Kathleen Fraser, and Svetlana Kiritchenko. 2024. Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19548–19564, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse (Guo et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1090.pdf