评估人机安全:衡量有害能力提升的框架
Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift
AI总结:
本文提出通过测量前沿模型带来的有害能力提升,推动人中心的AI安全评估,提供系统性测量方法和行动步骤。
摘要:
当前前沿AI安全评估强调静态基准、第三方注释和红队测试。本文主张AI安全研究应聚焦于以人为中心的评估,测量有害能力提升:即用户在前沿模型下相较于传统工具所能造成危害能力的边际增加。我们将有害能力提升作为核心AI安全指标,基于社会科学研究基础,提供具体的方法论指导以系统性测量。最后,我们为开发者、研究人员、资助方和监管机构提供可行步骤,使有害能力提升评估成为标准实践。
英文摘要:
Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful capability uplift: the marginal increase in a user's ability to cause harm with a frontier model beyond what conventional tools already enable. We frame harmful capability uplift as a core AI safety metric, ground it in prior social science research, and provide concrete methodological guidance for systematic measurement. We conclude with actionable steps for developers, researchers, funders, and regulators to make harmful capability uplift evaluation a standard practice.
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。