“They are uncultured”: Unveiling Covert Harms and Social Threats in LLM Generated Conversations

Preetam Prabhu Srikar Dammu, Hayoung Jung, Anjali Singh, Monojit Choudhury, Tanu Mitra


Abstract
Large language models (LLMs) have emerged as an integral part of modern societies, powering user-facing applications such as personal assistants and enterprise applications like recruitment tools. Despite their utility, research indicates that LLMs perpetuate systemic biases. Yet, prior works on LLM harms predominantly focus on Western concepts like race and gender, often overlooking cultural concepts from other parts of the world. Additionally, these studies typically investigate “harm” as a singular dimension, ignoring the various and subtle forms in which harms manifest. To address this gap, we introduce the Covert Harms and Social Threats (CHAST), a set of seven metrics grounded in social science literature. We utilize evaluation models aligned with human assessments to examine the presence of covert harms in LLM-generated conversations, particularly in the context of recruitment. Our experiments reveal that seven out of the eight LLMs included in this study generated conversations riddled with CHAST, characterized by malign views expressed in seemingly neutral language unlikely to be detected by existing methods. Notably, these LLMs manifested more extreme views and opinions when dealing with non-Western concepts like caste, compared to Western ones such as race.
Anthology ID:
2024.emnlp-main.1134
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:
20339–20369
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1134
DOI:
10.18653/v1/2024.emnlp-main.1134
Bibkey:
Cite (ACL):
Preetam Prabhu Srikar Dammu, Hayoung Jung, Anjali Singh, Monojit Choudhury, and Tanu Mitra. 2024. “They are uncultured”: Unveiling Covert Harms and Social Threats in LLM Generated Conversations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20339–20369, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
“They are uncultured”: Unveiling Covert Harms and Social Threats in LLM Generated Conversations (Dammu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1134.pdf