arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.11986cs.AIcs.CLcs.CY
收藏

生成式人工智能系统的社会技术安全评估

Sociotechnical Safety Evaluation of Generative AI Systems

Google DeepMind(谷歌DeepMind)
Laura Weidinger, Maribeth Rauh, Nahema Marchal, Arianna Manzini, Lisa Anne Hendricks, Juan Mateos-Garcia, Stevie Bergman, Jackie Kay, Conor Griffin, Ben Bariach… 展开作者

Laura Weidinger, Maribeth Rauh, Nahema Marchal, Arianna Manzini, Lisa Anne Hendricks, Juan Mateos-Garcia, Stevie Bergman, Jackie Kay, Conor Griffin, Ben Bariach, Iason Gabriel, Verena Rieser, William Isaac

AI总结:

本文提出一个三层社会技术框架来评估生成式AI系统风险,在能力评估基础上增加人类交互和系统性影响层面,并调查现有评估、识别三大空白及提出改进路径。

摘要:

生成式人工智能系统会产生一系列风险。为确保生成式人工智能系统的安全,必须对这些风险进行评估。在本文中,我们为建立此类评估做出了两项主要贡献。首先,我们提出了一个三层框架,采用结构化的社会技术方法来评估这些风险。该框架涵盖能力评估,这是当前安全评估的主要方法。在此基础上,它进一步借鉴系统安全原则,特别是认识到上下文决定了特定能力是否可能造成伤害。为了考虑相关上下文,我们的框架将人类交互和系统性影响作为额外的评估层加入。其次,我们调查了生成式人工智能系统安全评估的现状,并创建了一个现有评估的存储库。从这一分析中浮现出三个突出的评估空白。我们提出了弥合这些空白的路径,概述了实际步骤以及不同参与者的角色和责任。社会技术安全评估是一种切实可行的方法,可对生成式人工智能系统进行稳健而全面的安全评估。

英文摘要:

Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a three-layered framework that takes a structured, sociotechnical approach to evaluating these risks. This framework encompasses capability evaluations, which are the main current approach to safety evaluation. It then reaches further by building on system safety principles, particularly the insight that context determines whether a given capability may cause harm. To account for relevant context, our framework adds human interaction and systemic impacts as additional layers of evaluation. Second, we survey the current state of safety evaluation of generative AI systems and create a repository of existing evaluations. Three salient evaluation gaps emerge from this analysis. We propose ways forward to closing these gaps, outlining practical steps as well as roles and responsibilities for different actors. Sociotechnical safety evaluation is a tractable approach to the robust and comprehensive safety evaluation of generative AI systems.

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。

↑