arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.05377cs.AI
收藏

大型语言模型群体中的集体创新

Collective Innovation in Groups of Large Language Models

IT University, Denmark(丹麦信息技术大学);Microsoft Research, United States(微软研究院);Inria Center of the University of Bordeaux, France(波尔多大学法国国家信息与自动化研究所中心)

Eleni Nisioti, Sebastian Risi, Ida Momennejad, Pierre-Yves Oudeyer, Clément Moulin-Frier

AI总结:

本文以玩《Little Alchemy 2》的 LLM 为智能体研究集体创新,发现动态连接群体优于全连接群体,并指出 LLM 的能力、局限及人机协同创新的研究方向。

摘要:

人类文化依赖于集体创新:我们不断探索如何将环境中的现有元素组合起来以创造新元素的能力。语言被假设在人类文化中发挥关键作用,既驱动个体认知能力,也塑造交流。然而,大多数集体创新模型都不赋予智能体认知能力或语言能力。在此,我们贡献了一项关于集体创新的计算研究,其中智能体是大型语言模型(LLM),它们玩《Little Alchemy 2》这款最初为人类开发的创意电子游戏;我们认为,该游戏捕捉了以往测试平台所不具备的、与创新景观有关的有用方面。我们首先研究孤立状态下的 LLM,发现它既表现出有用的技能,也存在关键局限。随后,我们研究共享与其行为相关信息的 LLM 群体,并关注社会连接性对集体绩效的影响。与以往的人类研究和计算研究一致,我们观察到具有动态连接性的群体优于全连接群体。随着生成式人工智能算法与人类并肩创新,我们的工作揭示了未来集体创新研究的机遇与挑战,这些研究正变得日益重要。

英文摘要:

Human culture relies on collective innovation: our ability to continuously explore how existing elements in our environment can be combined to create new ones. Language is hypothesized to play a key role in human culture, driving individual cognitive capacities and shaping communication. Yet the majority of models of collective innovation assign no cognitive capacities or language abilities to agents. Here, we contribute a computational study of collective innovation where agents are Large Language Models (LLMs) that play Little Alchemy 2, a creative video game originally developed for humans that, as we argue, captures useful aspects of innovation landscapes not present in previous test-beds. We, first, study an LLM in isolation and discover that it exhibits both useful skills and crucial limitations. We, then, study groups of LLMs that share information related to their behaviour and focus on the effect of social connectivity on collective performance. In agreement with previous human and computational studies, we observe that groups with dynamic connectivity out-compete fully-connected groups. Our work reveals opportunities and challenges for future studies of collective innovation that are becoming increasingly relevant as Generative Artificial Intelligence algorithms and humans innovate alongside each other.

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。

↑