Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
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.
Auditing LLM judge reliability and defining trustworthy verdict rate and accuracy upper bound
Published Oct 8
Evaluated models GPT-5.2 , GPT-4o , Gemini-2.5-Pro and others6 Abstract The authors claim that comparing judges should look at T, not just accuracy.The authors audit whether LLM-as-a-Judge decisions can still be treated as actionable ground truth under repeated queries, swapped candidate order, and changed prompt formats.
揭示安全路由评测在分布偏移下的虚假下限与选择偏差
Published Oct 1
Evaluated models claude-3-5-sonnet , claude-3-opus , claude-sonnet-4-6 and others9 Abstract 论文揭示安全路由评估在分布偏移下的虚假下限，指出防御重心应转向外部动作级强制。
诊断护栏相对基座在对抗提示上的置信失校
Published Sep 29
Evaluated models Llama-Guard 7B , Llama-Guard-2 8B , Llama-Guard-3 8B and others10 Abstract 对抗包装使 guard 高置信漏检，而对应 base 在同一输入上常更不确定。诊断性分析 ：五个提示词分类 guard 的置信度，在清洁输入上可以较校准，在越狱包装后则变成高置信度的错误判定。
提出 RewardExplainer，用反事实偏好反馈学习奖励模型解释
Published Sep 28
Evaluated models FsfairX-LLaMA3-RM-v0.1 , Skywork-Reward-V2-Qwen3-1.7B , RM-Mistral-7B and others6 Abstract RewardExplainer 用双向反事实反馈训练 RM 解释器，并用以发现偏差、定向微调原 RM。RewardExplainer 针对只输出标量的判别式奖励模型，训练一个可复用的自然语言机制解释器，并把解释接到偏差发现与 RM 微调上。
分析稀疏重叠下 LLM judge 与人类一致性的验证误差并规划重叠分配
Published Sep 26
Evaluated models Gemini Flash , Gemini Pro , GPT-4o-mini and others10 Abstract 稀疏重叠主导 judge 验证的错误决策。这篇工作研究标注重叠很稀时，怎样验证 LLM judge 是否足以替代人类，并规划重叠该留多少、怎么分配。 。部署前的标准做法是在校准集上比较 judge 与人类的一致性。
归纳开放式医学长答案检索核验的失败分类
Published Sep 25
Evaluated models GPT-5.4 , Mistral Small 3 (24B-Instruct-2501) , Mistral Small 4 (119B-2603) and others8 Abstract 作者把开放式低召回归为证据是否在库、能否被定位，以及与声明是否对齐。这篇工作诊断开放式医学事实核验的 retrieve-then-verify 管线断在哪里，而不是提出新的核验器。
提出 harm laundering，证明安全训练改写而非消除性别歧视
Published Sep 18
Evaluated models gpt2 , gpt2-medium , gpt2-large and others15 Abstract GPT 谱系上毒性下降与表征伤害上升并存。Wyer、Black 与 Al Moubayed 用 OpenAI GPT 谱系检验：毒性分数下降是否等于歧视减少。 他们的答案是否定的，并把“显性伤害被改写成评测指标看不见的形式”称为 harm laundering。
You have reached the end