Skip to contentSkip to filters

We use cookies for analytics.

Why Pretrained Models Hallucinate

Santosh Vempala

Georgia Institute of Technology

Recording

44 min

Abstract

This talk analyzes hallucination in language models from a mathematical perspective and shows that the statistical pressures of the next-word-prediction training pipeline induce hallucinations under fairly general conditions, even when models are trained on clean data. The core proof is a simple reduction from a natural classification task, deciding whether a statement is a fact or a hallucination, to a generation or prompt-completion task.

Topics