提出交互主义范式，理解大模型集体行为的形成机制。
Generative AI collective behavior needs an interactionist paradigm
- 用交互主义视角分析大模型在社会语境中如何受先验知识影响
- 强调多智能体系统中认知与社会因素的动态互构
- 适合关注AI伦理、社会影响的研究者与政策制定者
本文认为，理解基于大语言模型（LLMs）的智能体集体行为是一项关键研究课题，其影响涉及社会多个层面的风险与机遇。我们指出，LLMs具有海量预训练知识和隐含社会先验，并可通过上下文学习实现适应性调整，这一独特性质要求建立一种交互主义范式——包含新的理论基础、研究方法和分析工具，以系统考察先验知识与嵌入价值如何与社会情境相互作用，塑造多智能体生成式AI系统中的涌现现象。本文提出并讨论了四个对构建与部署基于LLM的集体系统至关重要的方向，涵盖理论、方法及跨学科对话。
原文摘要 · Abstract (English)
In this article, we argue that understanding the collective behavior of agents based on large language models (LLMs) is an essential area of inquiry, with important implications in terms of risks and benefits, impacting us as a society at many levels. We claim that the distinctive nature of LLMs--namely, their initialization with extensive pre-trained knowledge and implicit social priors, together with their capability of adaptation through in-context learning--motivates the need for an interactionist paradigm consisting of alternative theoretical foundations, methodologies, and analytical tools, in order to systematically examine how prior knowledge and embedded values interact with social context to shape emergent phenomena in multi-agent generative AI systems. We propose and discuss four directions that we consider crucial for the development and deployment of LLM-based collectives, focusing on theory, methods, and trans-disciplinary dialogue.
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。