"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909196217221120 |
|---|---|
| author | Dammu, Preetam Prabhu Srikar Jung, Hayoung Singh, Anjali Choudhury, Monojit Mitra, Tanushree |
| author_facet | Dammu, Preetam Prabhu Srikar Jung, Hayoung Singh, Anjali Choudhury, Monojit Mitra, Tanushree |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_05378 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | "They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations Dammu, Preetam Prabhu Srikar Jung, Hayoung Singh, Anjali Choudhury, Monojit Mitra, Tanushree Computation and Language Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning 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. |
| title | "They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations |
| topic | Computation and Language Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2405.05378 |