Abstract:Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive expert. Existing cascades delegate based on probe uncertainty, but uncertainty is a poor proxy for delegation benefit, as it ignores whether the expert would actually correct the error. To address this problem, we introduce Calibrate-Then-Delegate (CTD), a model-cascade approach that provides probabilistic guarantees on the computation cost while enabling instance-level (streaming) decisions. CTD builds on a novel delegation value (DV) probe, a lightweight model operating on the same internal representations as the safety probe that directly predicts the benefit of escalation. To enforce budget constraints, CTD calibrates a threshold on the DV signal using held-out data via multiple hypothesis testing, yielding finite-sample guarantees on the delegation rate. Evaluated on four safety datasets, CTD consistently outperforms uncertainty-based delegation at every budget level, avoids harmful over-delegation, and adapts budget allocation to input difficulty without requiring group labels.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.14251 [cs.LG] |
| (or arXiv:2604.14251v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.14251 arXiv-issued DOI via DataCite |
From: Edoardo Pona [view email]
[v1]
Wed, 15 Apr 2026 11:05:59 UTC (217 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。