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

arXiv:2405.05378v1 Announce Type: cross
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 …

abstract applications arxiv assistants biases conversations cs.ai cs.cl cs.cy cs.hc cs.lg enterprise enterprise applications generated integral language language models large language large language models llm llms modern part prior recruitment research social threats tools type utility