On Large Language Models' Hallucination with Regard to Known Facts

arXiv:2403.20009v1 Announce Type: cross
Abstract: Large language models are successful in answering factoid questions but are also prone to hallucination.We investigate the phenomenon of LLMs possessing correct answer knowledge yet still hallucinating from the perspective of inference dynamics, an area not previously covered in studies on hallucinations.We are able to conduct this analysis via two key ideas.First, we identify the factual questions that query the same triplet knowledge but result in different answers. The difference between the model behaviors on …

abstract arxiv cs.cl cs.lg dynamics facts hallucination hallucinations inference knowledge language language models large language large language models llms perspective questions regard studies type