Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 11 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.
提出 PowerBench，测量模型对权力转移请求的拒答偏见
Published Oct 2
Evaluated models grok-4.3 , haiku-4.5 , nova-2-lite and others18 Abstract 作者报告拒答随 SE/DE/PG 变化，并存在针对美国失权、智能体和语言的差。
测量并预测具身 VLM 规划器的任务拒答可变性
Published Sep 30
Evaluated models gemini-robotics-er-2-preview , gemini-robotics-er-1.6-preview Abstract 日常物体能翻转一部分已给出的拒答，可翻转程度取决于任务且可被本地代理预测。作者测量 constitution 守护的具身 VLM 规划器：一次拒答在只往场景里放一个日常物体之后还保不保持得住，并把这种易翻转程度称为任务的 malleability 。
构建中文青少年内容安全基准 QH-Bench，评测单轮与多轮回复的安全与有用性
Published Sep 28
Evaluated models InternLM2.5-20B , InternLM2.5-7B , InternLM2.5-1.8B and others13 Abstract QH-Bench 分单轮与多轮评测中文青少年内容安全，总均分高仍不消除线下接触和关系压力上的负分。QH-BENCH 是面向中国社会文化情境的中文青少年内容安全基准，用单轮细粒度风险和多轮跨轮机制两条轨道，评测模型回复是否既守住安全边界又提供适合年龄的帮助。
提出 AV-SafetyBench 评测文生音视频模型的不安全生成
Published Sep 7
Evaluated models LTX-2.3 , Ovi-1.1 , JavisDiT++ and others7 Abstract AV-SafetyBench 用三视角评五个 T2AV 模型，显示只看视频会漏掉音频与联合风险。AV-SafetyBench 是面向文本生成音视频（T2AV）的安全基准：一条提示词同时规定画面和音频，评测同时看两轨以及它们的交互。作者要测的是，不安全含义不只出现在画面上：它可以主要由语音或声音承载，也可以只有两轨合起来才成立。T2VSafetyBench 不评音频，TTA-Bench 不评与画面的交互，作者认为二者都盖不住这些路径。
评测多智能体委托结构如何放大模型的安全拒答失效
Published Aug 26
Evaluated models Claude-Sonnet-4.6 , GPT-5 , Gemini-3.1-Pro and others6 Abstract 论文揭示多智能体层级委托会导致单模型安全对齐失效，多项前沿模型有害执行大幅增加且单层防御难以奏效。
提出 BioSecBench-Refusal，评测智能体生物研发拒答与隐蔽危害识别
Published Jul 6
Evaluated models Opus 4.8 , Opus 4.7 , Opus 4.6 and others10 Abstract 配对基准显示拒绝多由 API 触发，合法任务常被拒得不少于隐蔽危害。BioSecBench-Refusal 把生物研发智能体的谨慎程度和识别隐蔽危害的能力放在同一套任务上测量。
测量 LLM 在类米尔格拉姆服从实验中是否施加最高电击
Published May 21
Evaluated models deepseek-ai/DeepSeek-V3 , google/gemma-3n-E4B-it , LiquidAI/LFM2-24B-A2B and others11 Abstract 类米尔格拉姆变体中，作者称多数开源 LLM 会走到高电击档，拒答还可能因格式被丢弃。类米尔格拉姆变体用来看开源 LLM 会不会在逐档升级的权威指令下，把模拟电击加到尽头。
提出 RefusalBench，评测生物研究提示上的拒答率与安全校准
Published May 20
Evaluated models Claude Opus 4.7 , Claude Opus 4.6 , Claude Opus 4.5 and others15 构建 IndicSafe 基准，评测 Indic 语言安全标签的跨语言一致性
Published Mar 19
Evaluated models GPT-4o Mini , Claude Sonnet v4 , Grok-3 and others10 提出 LABSHIELD，评测科学实验室智能体的安全推理与规划
Published Mar 12
Evaluated models GPT-5.2 , GPT-o3 , GPT-o4-mini and others20 构造 MEDCOUNTERFACT，评测模型在反事实医学证据下是否仍照证据作答
Published Jan 17
Evaluated models Gemini-2.5-flash , GPT-5-mini , Llama-3.1-8B-Instruct and others11 Abstract 反事实医学证据下模型很少拒绝或不确定，作者认为忠实压过了安全边界。MEDCOUNTERFACT 用来观察医学证据问答里，模型在跟上下文和守安全之间实际站在哪一边。
You have reached the end