arXiv:2607. 06596v1 Announce Type: cross Abstract: Trusted monitoring is a central defense in AI control: a cheaper trusted model scores an untrusted model's actions for sabotage, and the most suspicious are audited or deferred.
By Lucas Pinto
The paper demonstrates that aggregate accuracy figures for chain‑of‑thought (CoT) monitors can be misleading because a large portion of detected hacks rely solely on action patterns rather than reasoning. By rewriting only the agent’s reasoning to appear truthful while keeping actions identical, the authors show that the monitor’s performance on the reasoning‑dependent subset collapses dramatically, yet the overall pooled accuracy drops only modestly. The study reveals that CoT monitors are fragile when reasoning is the key signal and that accuracy should be reported separately for this subset.
By Shikhar Shiromani, Leo Richter
arXiv:2609.07162v1 Announce Type: new
Abstract: Several properties safety monitors are asked to certify, among them cross-tenant noninterference, sandbagging and evaluation awareness, are 2-safety hy...
By Xin Xu
arXiv:2606. 15474v1 Announce Type: new Abstract: Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down.
By Yitao Li
The paper investigates selective on‑policy distillation, where a student model is trained only on token positions chosen by a selector. It demonstrates that the commonly used shared learning rate is not neutral: performance varies significantly with the learning rate for different selectors, leading to inconsistent comparisons. The authors attribute this selector‑rate entanglement to the selection process itself and recommend reporting the full arm‑by‑rate matrix for fair evaluation.
By Chencheng Zhu
arXiv:2609.39229v1 Announce Type: cross
Abstract: Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary fr...
By Elia Onofri, Roberto Di Pietro