HALO: An Ontology for Representing and Categorizing Hallucinations in Large Language Models

arXiv:2312.05209v2 Announce Type: replace-cross
Abstract: Recent progress in generative AI, including large language models (LLMs) like ChatGPT, has opened up significant opportunities in fields ranging from natural language processing to knowledge discovery and data mining. However, there is also a growing awareness that the models can be prone to problems such as making information up or `hallucinations', and faulty reasoning on seemingly simple problems. Because of the popularity of models like ChatGPT, both academic scholars and citizen scientists have documented …

abstract arxiv chatgpt cs.ai cs.cl data data mining discovery fields generative hallucinations halo however knowledge language language models language processing large language large language models llms mining natural natural language natural language processing ontology opportunities processing progress type