arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.04299cs.AI
收藏

通过专家启发将AI基准数据映射为定量风险估计

Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation

SaferAI(赛飞AI);Univ. Rennes(雷恩大学);Inria(法国国家信息与自动化研究所)

Malcolm Murray, Henry Papadatos, Otter Quarks, Pierre-François Gimenez, Simeon Campos

AI总结:

本文提出利用现有AI基准(如Cybench)结合专家启发生成概率估计,将LLM能力映射为定量风险,并通过试点研究验证该方法在AI风险评估中的可行性与改进方向。

摘要:

文献和多位专家指出,大型语言模型(LLMs)存在许多潜在风险,但关于其实际造成危害的直接测量仍然非常少。迄今为止,AI风险评估主要侧重于测量模型的能力,但模型的能力只是风险的指标,而非风险的度量。对AI风险场景进行更好的建模和量化,有助于弥合这一脱节,并将LLMs的能力与切实的现实世界危害联系起来。本文通过展示如何利用现有AI基准来促进风险估计的生成,为该领域做出了早期贡献。我们描述了一项试点研究的结果,在该研究中,专家们使用来自AI基准Cybench的信息来生成概率估计。我们表明,该方法在这一目的上似乎很有前景,同时指出了可以做出的改进,以进一步加强其在定量AI风险评估中的应用。

英文摘要:

The literature and multiple experts point to many potential risks from large language models (LLMs), but there are still very few direct measurements of the actual harms posed. AI risk assessment has so far focused on measuring the models' capabilities, but the capabilities of models are only indicators of risk, not measures of risk. Better modeling and quantification of AI risk scenarios can help bridge this disconnect and link the capabilities of LLMs to tangible real-world harm. This paper makes an early contribution to this field by demonstrating how existing AI benchmarks can be used to facilitate the creation of risk estimates. We describe the results of a pilot study in which experts use information from Cybench, an AI benchmark, to generate probability estimates. We show that the methodology seems promising for this purpose, while noting improvements that can be made to further strengthen its application in quantitative AI risk assessment.

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。

↑