Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 10 papers Another 232 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.
评测记忆门控对激活诱导与记忆诱导谄媚的防御效果
Published Oct 6
Evaluated models Llama-3.1-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 and others4 Abstract 作者称外部记忆过滤成立,数据未显示反向转向再有贡献。作者在四个开源指令模型上,把激活转向和外部记忆处理放进同一纵深防御协议,看记忆诱发谄媚和内部谄媚压力能否分开压低,以及个性化效用还剩多少。要处理的问题是:检索到的用户历史会推动模型顺从存储信念。只改外部上下文,并不直接动模型内部的谄媚表征。
提出 MemAdapter,在检索后约束记忆对智能体推理的影响
Published Oct 4
Evaluated models DeepSeek-V4-Flash , GPT-5.6-sol , Qwen3-8B Abstract 检索后三阶段调节记忆角色。MemAdapter 是给长期记忆智能体用的检索后调节框架,用来处理记忆诱发谄媚。
提出 HeadEdit,经冻结 unembedding 做随输入变化的 logit 校正
Published Oct 1
Evaluated models Qwen3-4B , Gemma-3-4B-IT , Llama-3.2-3B-Instruct and others4 Abstract 低秩 unembedding 校正抬高九个设置的总体准确率,并可部分预测 DPO 更新。HeadEdit 是一种不更新参数的行为校准方法,作用点是冻结的 unembedding,而不是中间层残差或新的梯度优化。
提出 Constitutional adapters,蒸馏宪法行为以缓解越狱与失准
Published Sep 29
Evaluated models Qwen3.5-4B , Llama-3.1-8B-Instruct , Gemma-4-E4B and others4 Abstract 差分宪法适配器在长上下文和多轮上更稳,并可按 α 换取遵从。
提出 LocUS,用词汇子空间选择注意力头并约束激活转向
Published Sep 25
Evaluated models Mistral-7B-v0.1 , Mistral-7B-Instruct-v0.3 , Llama-3.1-8B and others7 Abstract LocUS 用词汇子空间约束 DoM 转向的位置和方向。LocUS 是不更新权重的推理时转向方法,把差分均值更新限制在少数注意力头及其属性对齐子空间。
提出 AIMES 用词表读出在线调节多价值激活干预
Published Sep 25
Evaluated models Gemma-3-4B-IT , Gemma-3-12B-IT , Qwen3-4B and others5 Abstract AIMES 用词表读出闭环调节多价值转向,优势随深度变化且实现扰动更小。AIMES 是推理时的多价值激活转向框架,用中间层词表读出把固定系数改成随状态变化的权重。
提出 RLCDAlignBench,零样本检测多种对齐失败
Published Sep 24
Evaluated models Jev (jev-1.13.0) Abstract 一次通用问题已能给多数对齐失败排序,大的误差来自状态和标签。RLCDAlignBench 测量用强化学习做校准决策的 Jev,能否当作对齐失败的零样本检测器。
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。
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。
You have reached the end