Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations

arXiv:2404.03745v1 Announce Type: cross
Abstract: The widespread adoption and transformative effects of large language models (LLMs) have sparked concerns regarding their capacity to produce inaccurate and fictitious content, referred to as `hallucinations'. Given the potential risks associated with hallucinations, humans should be able to identify them. This research aims to understand the human perception of LLM hallucinations by systematically varying the degree of hallucination (genuine, minor hallucination, major hallucination) and examining its interaction with warning (i.e., a warning of potential …

abstract adoption arxiv capacity concerns cs.ai cs.cl cs.hc effects engagement fakes hallucinations human humans identify language language models large language large language models llm llm hallucinations llms perception risks them type