CreativityPrism: a holistic benchmark for large language model creativity

Abstract

Creativity is often seen as a hallmark of human intelligence. While large language models (LLMs) are increasingly perceived as producing creative text, there is still no holistic framework to evaluate their creativity across diverse scenarios. Existing evaluation methods remain fragmented, with dramatic variation across domains and tasks, largely due to differing definitions and measurements of creativity. Inspired by the hypothesis that creativity is not one fixed idea, we propose CreativityPri

Relevance Assessment

Research Gap

Notes are automatically saved as you type

Search Queries