arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.01623cs.AIcs.CL
收藏

AI能像人类一样有创造力吗?

Can AI Be as Creative as Humans?

National University of Singapore(新加坡国立大学);Stanford University(斯坦福大学);Google DeepMind(谷歌DeepMind);Microsoft Research(微软研究院);Rutgers University(罗格斯大学);University of Pennsylvania(宾夕法尼亚大学);Columbia University(哥伦比亚大学)

Haonan Wang, James Zou, Michael Mozer, Anirudh Goyal, Alex Lamb, Linjun Zhang, Weijie J Su, Zhun Deng, Michael Qizhe Xie, Hannah Brown, Kenji Kawaguchi

AI总结:

本文提出相对创造力与统计创造力框架,理论证明AI若能充分拟合人类创作的条件数据,即可达到与人类创作者相当的创造力,并给出LLM评估与训练指导。

摘要:

创造力是社会进步和创新的基石。随着先进生成式AI模型的兴起,它们已经能够完成曾经被认为专属于人类创造力的任务,因此研究AI的创造潜力对于其负责任的开发与应用变得势在必行。本文在理论上证明:在能够恰当拟合人类创作者所生成数据的条件下,AI可以像人类一样具有创造力。因此,关于AI创造力的争论可归结为其拟合足够数量数据的能力问题。为得出这一结论,本文首先通过引入“相对创造力”这一新概念来处理创造力定义中的复杂性。我们并不试图给出创造力的普适定义,而是将关注点转向AI是否能够匹配一个假设人类的创造能力。这一方法论转变带来了对AI创造力在统计上可量化的评估,称为“统计创造力”。该概念通过在统计上比较AI与特定人类群体的创造能力,促进了对AI创造潜力的理论探索。我们的分析表明,通过拟合大量条件数据,而不将生成条件边缘化消去,AI可以成为一个假设的新创作者。该创作者具备与其所训练的人类创作者同等水平的创造能力。基于这些理论发现,我们讨论了在提示条件自回归模型中的应用,为评估大型语言模型(LLM)等生成式AI模型的创造能力提供了一种实用手段。此外,本研究还提供了可操作的训练指南,在创造力的理论量化与实际模型训练之间建立桥梁。

英文摘要:

Creativity serves as a cornerstone for societal progress and innovation. With the rise of advanced generative AI models capable of tasks once reserved for human creativity, the study of AI's creative potential becomes imperative for its responsible development and application. In this paper, we prove in theory that AI can be as creative as humans under the condition that it can properly fit the data generated by human creators. Therefore, the debate on AI's creativity is reduced into the question of its ability to fit a sufficient amount of data. To arrive at this conclusion, this paper first addresses the complexities in defining creativity by introducing a new concept called Relative Creativity. Rather than attempting to define creativity universally, we shift the focus to whether AI can match the creative abilities of a hypothetical human. The methodological shift leads to a statistically quantifiable assessment of AI's creativity, term Statistical Creativity. This concept, statistically comparing the creative abilities of AI with those of specific human groups, facilitates theoretical exploration of AI's creative potential. Our analysis reveals that by fitting extensive conditional data without marginalizing out the generative conditions, AI can emerge as a hypothetical new creator. The creator possesses the same creative abilities on par with the human creators it was trained on. Building on theoretical findings, we discuss the application in prompt-conditioned autoregressive models, providing a practical means for evaluating creative abilities of generative AI models, such as Large Language Models (LLMs). Additionally, this study provides an actionable training guideline, bridging the theoretical quantification of creativity with practical model training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑