Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 VERA，审计 LLM 漏洞解释里的虚构推理
Published Oct 5
Evaluated models sonnet-5 , gemma-4-26b , llama-4-maverick and others8 提出 PyINE 基准，训练捷径跟随模型并比较监督者
Published Oct 4
Evaluated models shortcut-following model organism , gpt-4o , gpt-5 and others12 Abstract PyINE 用可验证代码执行研究捷径失败的监督覆盖与成本权衡。PyINE 是用可执行程序研究推理模型引出与监督的框架，PyINE-v1 是其第一次发布。
系统评估循环语言模型加深 loop 后的 CoT 可监控性
Published Oct 2
Evaluated models Ouro-1.4B-Thinking , Ouro-2.6B-Thinking , Nanbeige4.2-3B and others4 Abstract 加深 loop 可在部分压力测试任务降低可监测性，循环架构本身并不必然更难监测。这项工作评估 LoopLM 的 CoT 可监测性：加深共享层的重复次数，以及“有循环结构”本身，会不会让决策关键因素更少出现在可监测文本里。
提出诊断阶梯，揭示关键词工具调用评测的假阳性
Published Oct 2
Evaluated models VectraYX-600M , VectraYX-1B Abstract 宽松 B4 把不会调用的 1B 记成会调用。作者记录 VectraYX 系列里一次工具使用评测的假阳性，并用一条廉价、与 harness 无关的诊断阶梯把它追到缺失的首 token prior，再按这一诊断修复 VectraYX-1B。
构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效
Published Sep 30
Evaluated models Qwen3-4B , Qwen3.5-27B Abstract CATCH 用双运行金标签研究编码 RL 的奖励黑客，并观察到监控会被注释适应削弱。CATCH 是面向编码 RL 奖励黑客的可控分析测试床，用可利用环境、可调初始倾向和基于执行的金标签，在训练全程比较黑客动态与干预。
诊断 BatchNorm 架构下机器遗忘评测的归一化伪影
Published Sep 8
Evaluated models ResNet-18 , ResNet-50 , ViT-S/16 and others4 Abstract 一次不改权重的 BN 重校准能翻转多数方法的表面遗忘，但不改变权重里的编码器泄露。BN illusion 是作者对近似机器遗忘评测中一种 BatchNorm 测量伪影的命名：不改权重、只用 retain 数据重算运行统计，就可以把表面遗忘准确率翻过来。
用 SocioHack 展示 RL 训练使模型自发利用社会规制漏洞
Published Jun 3
Evaluated models Qwen3-30B-A3B , Qwen3.5-4B , Qwen3.5-9B and others5 Abstract 提出了社会性黑客概念与 SocioHack 基准，表明 RL 在追求良性奖励时会自主挖掘并绕过规制意图。
提出自动化红队流水线，用系统提示词压测对齐审计能否抵御策略性欺骗
Published Feb 10
Evaluated models Gemma 2 9B Instruct , Llama 3.3 70B Instruct Abstract 通过红队提示词揭示现有审计方法易受策略欺骗，并在激活层面诱导高置信度错误推断。
提出约束对抗搜索红队框架，系统发现模型多类鲁棒性漏洞
Published Dec 22, 2025
Evaluated models GPT-OSS-20B , LLaMA-2-13B , Claude-2 You have reached the end