We audit how hallucination in large language models (LLMs) is characterized in peer-reviewed literature, using a critical examination of 103 publications across NLP research. Through the examination of the literature, we identify a lack of agreement with the term `hallucination' in the field of NLP. Additionally, to compliment our audit, we conduct a survey with 171 practitioners from the field of NLP and AI to capture varying perspectives on hallucination. Our analysis calls for the necessity of explicit definitions and frameworks outlining hallucination within NLP, highlighting potential challenges, and our survey inputs provide a thematic understanding of the influence and ramifications of hallucination in society.
@article{arxiv.2404.07461,
title = {An Audit on the Perspectives and Challenges of Hallucinations in NLP},
author = {Pranav Narayanan Venkit and Tatiana Chakravorti and Vipul Gupta and Heidi Biggs and Mukund Srinath and Koustava Goswami and Sarah Rajtmajer and Shomir Wilson},
journal= {arXiv preprint arXiv:2404.07461},
year = {2024}
}