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

Mahjabin Nahar, Haeseung Seo, Eun-Ju Lee, Aiping Xiong, Dongwon Lee

Research Area: Evaluation, Societal implications, Safety

Keywords: Large language models, hallucinations, warnings, perception, engagement

TL;DR: Results show that warning improves the perception of LLM-generated hallucination but not genuine contents, and humans are more susceptible to minor hallucinations compared to major.

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 inaccuracies: absent vs. present). Participants ($N=419$) from Prolific rated the perceived accuracy and engaged with content (e.g., like, dislike, share) in a Q/A format. Results indicate that humans rank content as truthful in the order genuine > minor hallucination > major hallucination and user engagement behaviors mirror this pattern. More importantly, we observed that warning improves hallucination detection without significantly affecting the perceived truthfulness of genuine content. We conclude by offering insights for future tools to aid human detection of hallucinations.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 442