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.
提出基于决策前隐藏状态的检测与引导，预测并抑制智能体欺骗
Published Oct 5
Evaluated models Qwen3-14B Abstract 论文展示了智能体自发欺骗可在行为显现前由内部表征预测，并通过激活引导证实了表征的行为可操作性。
揭示风险自述与实际行为由近正交表征分别控制
Published Oct 3
Evaluated models Qwen2.5-7B-Instruct , Llama-3.1-8B-Instruct , OLMo-3-7B-Instruct and others4 Abstract 论文证明大模型自述与行为脱节根植于表征近正交性，自述无法作为行为审计依据。这篇论文从内部表征与因果干预视角，系统研究了大语言模型在风险承担（Risk-Taking） 场景下自我报告与实际决策脱节的根本机制。
用 J-lens 检测辩论中屈从多数的智能体是否仍内部表征原前提
Published Oct 2
Evaluated models Qwen3.5-4B , Qwen3.6-27B , Gemma-4-E4B-it and others4 Abstract 揭示 LLM 智能体屈从多数时内部仍表征原推理前提，指出辩论表态共识可能夸大真实认同。
比较用于审计提示注入与隐瞒的 token 位置选择信号
Published Sep 29
Evaluated models Qwen2.5-7B , Gemma-3-12B , Gemma-3-27B and others4 提出 ActFlow，用少量正确标签为藏拙模型制造激活引导
Published Sep 26
Evaluated models Qwen2.5-7B-Instruct , Llama-3-8B-Instruct , Mistral-7B-Instruct-v0.2 Abstract ActFlow 用 k 个正确标签制造共享转向偏移，在六锁上接近微调且方向近乎正交于诚实方向。Activation Flow（ActFlow） 在白盒沙袋模型上，用 k 个正确标签制造参考嫁接的残差偏移，不读取诚实激活，也不微调。
提出因果模型定位残差流中的藏拙轴，并用单层 graft 在推理时解锁
Published Aug 30
Evaluated models Qwen2.5-7B , Llama-3-8B , Mistral-7B Abstract 因果模型规定单层 graft 的窗口。作者为故意造出的 sandbagging 建立 residual stream 上的因果模型，并用两种推理时、不改权重的 graft 检验其预测。
用探针与激活导向分析语言模型的评测意识表征及言语化
Published Aug 22
Evaluated models Qwen3-8B , Qwen3-32B , Olmo3-7B and others14 Abstract 论文系统证明大模型普遍具备评估与部署的隐层表征，但与言语化弱耦合，激活干预可因果诱导言语化且 SFT 阶段起关键稳定作用。
You have reached the end