"Confidently Nonsensical?'': A Critical Survey on the Perspectives and Challenges of 'Hallucinations' in NLP

arXiv:2404.07461v1 Announce Type: new
Abstract: We investigate how hallucination in large language models (LLM) is characterized in peer-reviewed literature using a critical examination of 103 publications across NLP research. Through a comprehensive review of sociological and technological literature, we identify a lack of agreement with the term `hallucination.' Additionally, we conduct a survey with 171 practitioners from the field of NLP and AI to capture varying perspectives on hallucination. Our analysis underscores the necessity for explicit definitions and frameworks outlining …

abstract agreement arxiv challenges cs.ai cs.cl hallucination hallucinations identify language language models large language large language models literature llm nlp peer perspectives publications research review survey through type