评估用户用前沿模型作恶能力的提升幅度,更真实反映AI安全风险。
Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift
- 以用户实际作恶能力提升为指标,取代静态测试。
- 提出可操作的方法框架,量化人类使用模型后危害能力增长。
- 适合开发者、监管者和研究者用于设计更安全的AI系统。
当前前沿AI安全评估侧重静态基准、第三方标注和红队测试。本文主张,AI安全研究应转向以人类为中心的评估,测量有害能力提升:即用户使用前沿模型后,其造成危害的能力相比传统工具的边际增长。我们将有害能力提升视为核心安全指标,基于已有社会科学研究进行理论支撑,并提供系统性测量的方法指导。最后,我们提出开发者、研究人员、资助方和监管机构可采取的具体行动,推动有害能力提升评估成为标准实践。
原文摘要 · Abstract (English)
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.
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。