跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 22:55 — 2026-11-20 22:55(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.20955

Jev-as-a-Reward: Validating Probabilistic Safety Judges for Reinforcement Learning

Eunkyeong Lee, Junhyung Moon, Seunggwan Hong, Dongsuk Oh

原文摘要

Probabilistic safety judges return the probability of a safety label and cheaply score reinforcement learning rollouts. A confidence gate sends only uncertain verdicts to a stronger LLM judge, which leaves confidently passed harm in a blind spot. Policies can exploit this blind spot, and commercial judges release new versions. We propose a protocol that validates such a judge before and during training, separates the share of confidently passed harm from its amount, and re-validates it after each judge change. We apply it to two versions of Jev, a commercial decision-only judge, and to an open guard classifier. Under the probability reward of Jev, passed harm shrinks in all 11 runs under the primary reference, mostly more slowly than caught harm, and concentrates in the blind spot. Binarizing this judge meets the escape criterion on Llama, and the open guard classifier shows an escape signal in one seed under a second reference. Guard classifiers share this blind spot, and even frontier LLM judges catch at most one of 10 human-labeled confident misses. Without a trained reward model, the probability reward with a helpfulness term lowers HarmBench attack success on Llama-3.1-8B from 0.287 to at most 0.033 at the final checkpoint.

cs.AI · cs.CL