| Download | - View final version: Adaptable moral stances of large language models on sexist content: implications for society and gender discourse (PDF, 1.7 MiB)
|
|---|
| Link | https://aclanthology.org/2024.emnlp-main.1090 |
|---|
| Author | Search for: Guo, Rongchen; Search for: Nejadgholi, Isar1ORCID identifier: https://orcid.org/0000-0001-6241-6114; Search for: Dawkins, Hillary1; Search for: Fraser, Kathleen C,1ORCID identifier: https://orcid.org/0000-0002-0752-6705; Search for: Kiritchenko, Svetlana1ORCID identifier: https://orcid.org/0000-0003-2550-3918 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), November 12-16, 2024, Miami, Florida, United States |
|---|
| 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. |
|---|
| Publication date | 2024-11 |
|---|
| Publisher | Association for Computational Linguistics |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 1de130fe-7cb4-4e5e-b85e-b5eefdc96273 |
|---|
| Record created | 2024-11-14 |
|---|
| Record modified | 2024-12-06 |
|---|
