System One Models 的校准与风险预算决策方法
Calibration and Risk-Budgeted Decisions with System One Models
一篇讲怎么给 LLM 审核和检索决策设风险阈值的论文，用 LTT 方法把超标率从一半降到 7.8%，做部署的可以看看。
这篇 arXiv 论文研究 LLM 工作流和智能体中的二元决策问题，例如允许/拦截输入、丢弃/保留检索文档，在没有人工兜底时不确定案例也必须给出动作。方法是在不确定时默认采取保守回退，并把效用最大化动作子集内的漏报风险控制在预算内。实验覆盖审核、安全、重排三类任务的 6 个数据集，对比通用 System One 模型、任务基线和本地开源权重复刻的 System One 模型。结果显示朴素阈值选择基线在约一半设定下超出目标风险，而采用有限样本统计保证的 Learn Then Test（LTT）仅 7.8% 的设定超标。
Calibration and Risk-Budgeted Decisions with System One Models
LLM workflows and agents rely on a set of binary decisions like allow/block an input, or discard/retain a retrieved document. When human deferral is unavailable, uncertain cases must still receive an action. We study System One decision scores in this setting by defaulting to a conservative fallback when uncertain, and controlling the false omission risk within the subset of inputs assigned the utility-maximizing action. Across six datasets covering moderation, safety, and reranking, we compare general System One models with task baselines and a local open-weights fine-tuned System One model. We show that naive baselines for threshold selection exceed the target risk in roughly half of settings with defined test risk, compared with 7.8\% for Learn Then Test (LTT), which leverages finite-sample statistical guarantees. Our results show why relying on a probability-like interface is insufficient for deployment decisions and how risk-budgeted selection trades useful action against observed error.
