arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.09402cs.CYcs.AIcs.GT
收藏

CERN for AI:面向自主的基于仿真的人工智能测试与对齐的理论框架

CERN for AI: A Theoretical Framework for Autonomous Simulation-Based Artificial Intelligence Testing and Alignment

The Institute for Artificial Intelligence Research and Development of Serbia(塞尔维亚人工智能研究与发展研究所);University of Belgrade(贝尔格莱德大学);University of Rome La Sapienza(罗马第一大学)

Ljubisa Bojic, Matteo Cinelli, Dubravko Culibrk, Boris Delibasic

AI总结:

本文提出基于虚拟现实与多智能体“数字公民”的仿真框架,融合多学科理论,用于测试和对齐LLM等AI系统,以提升其伦理一致性、可控性与社会责任感。

摘要:

本文探讨了采用多学科方法测试和对齐人工智能(AI)的潜力,尤其聚焦于大语言模型(LLM)。由于LLM的快速发展和广泛应用,这些模型的伦理对齐、可控性和可预测性等挑战已成为全球性风险。本研究考察了一个创新的、基于仿真的多智能体系统,该系统置于一个复制现实世界环境的虚拟现实框架之中。该框架由自动化的“数字公民”填充,通过模拟复杂的社会结构与互动来检验和优化AI。社会学、社会心理学、计算机科学、物理学、生物学和经济学等领域多种理论的应用,证明了构建更符合人类价值、更具社会责任感的AI的可能性。此类数字环境旨在提供一个动态平台,使先进AI智能体能够在其中互动并作出独立决策,从而模拟现实场景。这座数字城市中的行动者由LLM驱动,作为主要智能体,表现出高度的自主性。尽管该方法展现出巨大潜力,但仍存在显著挑战与局限,其中最突出的是现实世界社会动态的不可预测性。本研究致力于为AI的发展与完善作出贡献,并强调未来研究应整合社会、伦理和理论维度。

英文摘要:

This paper explores the potential of a multidisciplinary approach to testing and aligning artificial intelligence (AI), specifically focusing on large language models (LLMs). Due to the rapid development and wide application of LLMs, challenges such as ethical alignment, controllability, and predictability of these models emerged as global risks. This study investigates an innovative simulation-based multi-agent system within a virtual reality framework that replicates the real-world environment. The framework is populated by automated 'digital citizens,' simulating complex social structures and interactions to examine and optimize AI. Application of various theories from the fields of sociology, social psychology, computer science, physics, biology, and economics demonstrates the possibility of a more human-aligned and socially responsible AI. The purpose of such a digital environment is to provide a dynamic platform where advanced AI agents can interact and make independent decisions, thereby mimicking realistic scenarios. The actors in this digital city, operated by the LLMs, serve as the primary agents, exhibiting high degrees of autonomy. While this approach shows immense potential, there are notable challenges and limitations, most significantly the unpredictable nature of real-world social dynamics. This research endeavors to contribute to the development and refinement of AI, emphasizing the integration of social, ethical, and theoretical dimensions for future research.

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。

↑