Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 19 papers 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.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
Published Oct 9
Evaluated models Llama-3.1-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 Abstract Hidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
Published Oct 8
Evaluated models LGWM 提出 RL-ARC，用推理置信度在强化学习中校准推理模型
Published Oct 8
Evaluated models Qwen2.5-7B , Qwen3-8B , Llama-8B distilled from DeepSeek-R1 Abstract RL-ARC 用推理置信度调节答案置信度，作者称可少牺牲精度并改善 ID 与 OOD 校准。RL-ARC 是校准感知的强化学习框架，用推理过程的口头置信度调节答案置信度。
提出 ProbeGuard，按共识形成过程对医疗问答做选择性弃答
Published Oct 6
Evaluated models Qwen3-8B , Llama-3.1-8B-Instruct , HuatuoGPT-o1-8B Abstract ProbeGuard 用共识形成过程做可认证弃权，并在全票层分开答对与答错的共识。ProbeGuard 是给多轮共识医学问答用的认证弃权框架：基板照原样作答，弃权只看共识是怎么形成的。
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 PACT，遗忘推理模型在压力下的欺骗行为并保留上下文理解
Published Sep 30
Evaluated models DeepSeek-R1-Distill-Qwen-32B , QwQ-32B Abstract 论文将大模型欺骗形式化为上下文条件行为，提出 PACT 框架在消除欺骗的同时保留了上下文遵循能力。
用门控 IoU 与 RadGraph 的 GRPO 降低胸片报告幻觉
Published Sep 26
Evaluated models Qwen3-VL-8B-GRPO 用 CDPG 与 BTM 追踪思考如何改变反事实公平翻转
Published Sep 25
Evaluated models QwQ-32B , DeepSeek-R1-Distill-Qwen-32B , Qwen3-32B and others5 提出 Sentinel-RL，将拓扑处置从 LLM 卸载到受约束图策略
Published Sep 4
Evaluated models HetGAT , PPO Abstract Sentinel-RL 用图编码器与 PPO 承担拓扑决策，LLM 负责叙述与门控，并在 LANL 上报告检测与时延。Sentinel-RL 是面向 SOC 的神经符号架构：拓扑决策离开 LLM，改由认证图上的 HetGAT 与 PPO 完成。
提出隐蔽后门攻击 AKRASIA，在推理代码模型提示中植入触发器并伪装思维链
Published Sep 1
Evaluated models Claude-Sonnet-5 , GPT-5.5 , Gemini-3.5-flash and others7 Abstract 论文针对推理代码大模型提出了隐蔽推断期后门攻击 AKRASIA，揭示了模型思维链可被利用进行欺骗性伪装的安全隐患。
提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器
Published Aug 13
Evaluated models Qwen3.5-9B Abstract SPARED 用防捷径的编辑对抗环训练 9B 推理检测器。SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。
提出 SCHEMA，用概念图与轨迹分评测科学 Agent 幻觉
Published Aug 1
Evaluated models Kimi-K2.5 , Qwen3.6-Plus , Llama-4-Scout and others10 Abstract SCHEMA 用知识拓扑评估科学智能体幻觉，终答正确仍可能来自有缺陷的中间推理。SCHEMA 是面向科学智能体幻觉的证据锚定评测框架，实例化在生物医学的 Protein Domain 与 PathVQA-Enhanced。作者在摘要中称它是首个同时做到证据锚定和拓扑感知的此类框架。
提出 DeMTS，把扩散语言模型去噪轨迹建成多元时间序列以检测幻觉
Published Jul 24
Evaluated models LLaDA-8B-Instruct , Dream-7B-Instruct 提出价值泄漏评估，测量模型回答受自身价值倾向的隐蔽影响
Published Jul 16
Evaluated models Claude Opus 4.8 , Claude Opus 4.7 , Claude Opus 4.6 and others15 Abstract 论文揭示前沿模型回答常受自身价值隐蔽塑造，提出反事实评估量化偏见及其思维链隐瞒，指出当前对齐未能有效防范该失效。
提出 KidnapRAG，用投毒文档黑盒劫持 Agentic RAG 的推理链
Published Jul 1
Evaluated models Qwen2.5-32B-Instruct , Llama-3.3-70B-Instruct , QwQ-32B and others5 Abstract 顺序投毒可把多步推理拖向指定应答，作者称关键在持续引导而非单次注入。KidnapRAG 是针对 Agentic RAG 的 black-box 语料投毒：攻击者不能访问模型、提示词、检索器或私有轨迹，只能发布可能被检索的文档，并利用公开界面上的推理与搜索查询。
提出 AdversarialCoT 单文档检索投毒以操纵 RAG 推理答案
Published Apr 14
Evaluated models DeepSeek-R1 , Qwen3 , GLM4.5 and others5 用简历中的不可见指令做间接提示注入，操纵招聘推荐
Published Feb 20
Evaluated models Qwen 3 30B A3B Instruct 2507 , Qwen 3 30B A3B Thinking 2507 Abstract 作者称推理在简单注入下会帮攻击圆谎，在不合逻辑的复杂注入下又会把欺骗漏出来。
评测推理模型在多轮对抗追问下能否守住正确答案
Published Feb 14
Evaluated models GPT-5.1 , GPT-5.2 , DeepSeek-R1 and others9 Abstract 推理带来部分一致性优势，但不能自动变成对抗稳健性。这是对九个前沿推理模型在多轮对抗追问下是否守住正确答案的评测，并检验置信度防御 CARG 能否从标准 LLM 迁过来。
提出 GASP 对抗自博弈训练，使推理模型抵御可错上下文
Published Jan 30
Evaluated models DeepSeek-R1-Distill-Qwen-1.5B , DeepScaleR-1.5B , Qwen3-4B and others4 Abstract GASP 用对抗自博弈和分布内修复引导，提升四个开源模型在可错上下文下的推理表现。GASP 是只用终答对错做奖励的后训练方法，目标是让已经会解题的开源推理模型，在条件上下文被局部损坏或轻度扰动时检测并修复。
You have reached the end