Why language models hallucinate

T1Covered by 1 source · first reported by OpenAI News at 05 Sept 2025, 10:00 UTC

OpenAI’s new research explains why language models hallucinate. The findings show how improved evaluations can enhance AI reliability, honesty, and safety.

ai

Sources

• T1Why language models hallucinateOpenAI News05 Sept 2025, 10:00