人类多样性是创新源泉，但当前AI无法复制或维持这种多样性。
Human diversity fuels collective creativity that large language models cannot simulate or sustain
- 用母语和非母语写作者对比实验，发现非母语者贡献更多创意多样性。
- AI辅助写作使整体创意多样性下降，仅在优化个人想法时能保留多样性。
- 现有AI模型模拟人类创作池均低于真实人类表现，且高多样性伴随文本失真。
多样化的群体产生多样化思想，是创新的原始材料。生成式AI对这一机制构成双重挑战：日常使用可能使多元创作者趋于同质化，而AI模拟的多样性可能取代真实人类。我们通过预注册的创意隐喻实验，测试了母语（L1）与非母语（L2）英语写作者在无AI、AI生成想法（AI ideation）、AI优化自身想法（AI refinement）三种条件下的表现。结果显示，非母语写作者贡献的集体多样性高于母语者，且母语创作产生最丰富的创意池。AI ideation压缩了所有人的集体多样性，使非母语者的优势消失；而AI refinement则保留了多样性。随后，我们基于参与者真实背景构建人物角色，结合三类模型、母语提示和高采样温度，模拟整个写作者群体。所有模拟结果均低于真实人类群体，过度提升多样性仅导致退化的文本输出。在个体层面，AI ideation提升了写作者自我评分，形成私利与集体利益的矛盾，除非非母语者使用母语，此时双方受益。人类多样性仍是不可替代的创造性资源，当前AI无法模拟或维持；人机协作设计决定了其能否存续。
原文摘要 · Abstract (English)
Diverse human groups produce diverse ideas, the raw material of innovation. Generative AI challenges this engine twice over: everyday AI assistance may homogenize what diverse people create, and AI-simulated diversity may replace the people altogether. We tested both challenges in a preregistered creative metaphor experiment with native (L1) and non-native (L2) English writers, who wrote without AI, with AI-generated ideas (AI ideation), or with AI refining their own ideas (AI refinement). L2 writers contributed more collective diversity than L1 writers, with native-language ideation showing the most diverse pools. AI ideation compressed collective diversity for everyone and left the L2 advantage undetectable, whereas AI refinement preserved both. We then simulated the entire writer pool using personas built from participants' real backgrounds, three model families, native-language prompting, and elevated sampling temperatures. Every simulated pool fell below every human pool, and pushing models further induced diversity only through degenerate text. However, at the individual level, AI ideation raised writers' ratings, pitting private incentives against the collective good, except when L2 writers used their native language, which benefited both. Human diversity remains a valuable creative resource that current AI cannot simulate or sustain; the design of human-AI collaborative workflows determines whether it survives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。