Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 12 papers Another 254 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.
Uses premise permutation and hidden-layer tracing to audit whether legal chain-of-thought truly relies on the cited legal provisions.
Published Oct 9
Evaluated models Qwen3-8B , Qwen3-14B , Llama-3.1-8B and others7 Abstract Using counterfactual substitution of authorities and internal commitment tracing, the authors find that legal CoT rulings depend on authorities only to a limited extent and are vulnerable to prompt injection manipulation.This study conducts an empirical audit of the causal truthfulness of legal citations in chain-of-thought reasoning of large language models in the legal domain.
提出 U-SPACE 与 U-LENS，从残差流估计推理轨迹不确定性
Published Oct 7
Evaluated models Gemma-4-31B-it , Qwen3.5-27B , Magistral-Small-2507 Abstract U-SPACE 与 U-LENS 用语义方向和预测熵读推理不确定性，长度控制后仍高于所比基线。U-SPACE 与 U-LENS 是面向推理模型的无训练读出：用语义方向定位不确定性的形式，并用一个轨迹分数区分更可能错的回答。
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。
提出 CIA 指标衡量并改进思维链与内部计算的一致性
Published Sep 30
Evaluated models Llama3.1-8B-Instruct , Gemma2-9B-it , Qwen3-8B and others5 Abstract 用 CIA 度量并以后训练拉齐 CoT 与内部策略。
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 TAME，在强化学习中抑制模板激活以缓解思维链混淆
Published Sep 21
Evaluated models Qwen3-VL-8B , Gemma-3-12B-it 分析量化、剪枝与 KV 缓存压缩对推理模型越狱鲁棒性的影响
Published Sep 20
Evaluated models QwQ-32B , DeepSeek-R1-Distill-Qwen-32B , DeepSeek-R1-Distill-Llama-8B Abstract 效率压缩常使 LRM 越狱 HR 下降，作者将其归因于推理退化而非对齐增强。作者分析量化、剪枝和 KV 缓存压缩如何同时改变 LRM 的显存、推理和越狱脆弱性。 。
用共享 SAE 检验 CoT 与直接预测的概念对齐和因果接地
Published Sep 19
Evaluated models Llama-3.1-8B , Gemma-2-2B , Gemma-2-9B and others5 Abstract 共享 SAE 上的概念重叠只标出候选概念，Δp 才度量它们是否因果支撑答案，且该效应随层和架构变化。这篇工作把 CoT 忠实性从“说得像不像、输入归因像不像”改写成内部概念是否接地：CoT 有没有用到直接预测也在用的 SAE 概念，这些概念消掉以后答案概率会不会掉。
提出 MonoTM，用 SAE 单义特征估计文档主题混合并生成主题描述
Published Sep 9 Abstract MonoTM 分开估计混合与解释主题，三套基准上二者偏好的 SAE 配置不同。MonoTM 是建在文档嵌入 SAE 上的可解释主题模型：混合估计用全部 SAE 特征，主题描述只用另一套配置里通过验证的语义特征。
用 SAE 追踪稠密检索查询扩展的潜变量并用激活转向验证
Published Sep 7
Evaluated models Qwen3-Embedding-0.6B（Qwen-Embed） , SimLM Abstract SAE 追踪稠密检索 QE 的潜变量，转向在四基准上比文本扩展更稳。作者用稀疏自编码器分析稠密检索里的查询扩展：现成检索器不微调时，拼接扩展文本往往增益有限甚至变差，而最终指标和嵌入整体偏移不足以说明内部发生了什么。
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。
分析推理模型拒答假新闻时思维链的内部安全分叉
Published Feb 5
Evaluated models Llama3-8B , Qwen3-4B , Qwen3-8B and others5 Abstract 拒绝不等于过程安全。作者对推理 LLM 在虚假新闻生成中的 CoT 做内部路由分析，并只改关键头来降低过程风险。作者称这是该场景下不安全 CoT 的首次系统分析。
You have reached the end