Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 261 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.
AI summary 研究者提出一种轻量级路由 logits 安全检测器，在提示词预填充阶段读取 MoE 视觉语言模型的专家路由信号，在生成前判断多模态请求是否安全，且不修改模型参数或专家路由。
Published Oct 6
Evaluated models Qwen3-VL-30B-A3B-Instruct , Kimi-VL-A3B-Instruct Abstract 读出而非操纵 router logits，可在不改模型的情况下降低两模型的组合式安全错误。作者在两个指令微调 MoE VLM 上比较改模型与读路由。组合式风险按 HoliSafe 分成五类：图文各自可安全，合在一起才不安全，或不安全内容只在图像里。
用持续更新的探针做微调，降低有害性并保持线性可监测性
Published Sep 30
Evaluated models Mistral 7B Instruct v0.1 , Llama 3 8B Instruct Abliterated , Qwen3-14B Abstract 持续重拟合的探针可降低有害性、提高诚实性，训练后概念仍能被线性探针读出。Probe-guided fine-tuning 把探针分数当作唯一对齐信号，用来推动 harmlessness 与 honesty，并检查训练后这些概念是否仍线性可读。
提出有守卫最小步激活引导，只在关机语境把继续偏好转向接受关机
Published Sep 24
Evaluated models Qwen3.5-0.8B 提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权
Published Sep 15 Abstract 联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。
评估安全监视器并提出双侧梯级微调以减少会答有害请求的漏检
Published Sep 5
Evaluated models Gemma-4-31B-IT , Qwen3-32B , Llama Guard 3 8B and others6 Abstract 论文发现安全监视器大多拦截模型已拒答请求，指出明确度偏差是共性原因，并通过双侧梯级微调提升回答请求的召回表现。
在写入点定位拒答方向，经刚性旋转跨架构迁移并门控放大
Published Sep 4
Evaluated models Falcon-Mamba-7B , Falcon3-Mamba-7B , Llama-3.1-8B and others8 Abstract 拒答方向可经刚性旋转跨架构迁移，但必须在各架构的写入点读取。作者研究拒答表示是否随架构改变，结论是表示共享、读取位置随架构变。
提出 INTENT-AS-A-TOOL，用意图工具概率跟踪并干预智能体失准
Published Aug 28
Evaluated models Gemma-4-31B-IT , Qwen3.5-27B , Qwen3-235B-A22B and others5 Abstract 用意图工具的下一动作概率跟踪推理中的失准承诺，并在其成为首选时插入反思。Zhang 等人研究推理型语言模型在职场邮件沙箱里如何走向智能体失准，并提出用动作偏好而不是事后文本标签来跟踪承诺。问题是：有害执行往往出现在推理已经形成意图之后，但 CoT 监控是事后、粗粒度、依赖外部评审的，也看不到模型倾向调用哪个动作。
提出 Gram 审计框架，测量编程与研究智能体的破坏倾向
Published May 29
Evaluated models Gemini 2.5 Pro , Gemini 3.0 Pro Preview , Gemini 3.1 Pro Preview You have reached the end