Evaluating large language models for accuracy incentivizes hallucinations

Large language models sometimes produce confident, plausible falsehoods (“hallucinations”), limiting their reliability 1,2 . Prior work has offered numerous explanations and effective mitigations such as retrieval and tool use 3 , consistency-based self-verification 4 , and reinforcement learning from human feedback 5 . Nonetheless, the problem persists even in state-of-the-art language models 6,7 . …