False refusal

Also written: false refusals, over-refusal

A model refusing a request that was actually harmless, such as declining to explain how locks work.

Other terms from the same lesson

• constitutional AI: Training a model to critique and improve its own answers against a written set of principles.
• jailbreak: A prompt written to trick a model into ignoring its safety rules.
• RLAIF: Reinforcement learning from AI feedback: like RLHF, but an AI model applying written principles does the judging instead of people.