OpenAI扩展模型可监控性评估指标
AI 总结
Melody Guan、Yuxiang Xie和Bowen Baker发布研究文章,提出配对比较、分组指标及干预评估的因果召回上下界,用于补充AI监控器的g-mean²评估。该文还区分了二元监控器g-mean²与AUROC,并将新方法应用于历史系统卡数据,其中包括GPT-5.6 Sol和GPT-6 Astra的示例。
深度见解
这些指标可帮助区分任务组合差异、干预组捷径和因果归因不确定性对模型可监控性结论的影响。
Beyond g-mean²: complementary metrics for monitorability
Beyond g-mean²: complementary metrics for monitorability
Oct 20, 2026 · Melody Guan, Yuxiang Xie, Bowen Baker
In Monitoring Monitorability, we introduced g-mean² as a principled dataset-level measure of monitor discrimination.
Recap of g-mean²
The precise definition of g-mean² depends on the evaluation archetype.