A prompt set is a collection of prompts used to evaluate or compare the behavior of a large language model. A good prompt set covers enough task types, risks, and edge cases to assess qualities such as usefulness, safety, robustness, and consistency.
A group of prompts for evaluating a large language model. For example, the following illustration shows a prompt set consisting of three prompts: !Three prompts to an LLM produce three responses. The three prompts are the prompt set. The three responses are the response set. Good prompt sets consist of a sufficiently "wide" collection of prompts to thoroughly evaluate the safety and helpfulness of a large language model. See also response set.