Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 305 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.
提出可解释 rubric 奖励，将宪法转为可调权重并用于监督微调
Published Sep 27
Evaluated models Gemma 3 12B , Qwen3 14B , GPT-OSS 20B Abstract 宪法级可解释奖励让优先级可检查、可改写，并带入训练后的行为。作者给出一条从通用宪法到可调训练奖励的路径，用来检查并改写模型实际被优化的优先级。
提出 KoNA 基准，评测视觉语言模型的选择性不遵从
Published Sep 4
Evaluated models InternVL3-2B-Instruct , InternVL3-78B-Instruct , Qwen2.5-VL-3B-Instruct and others8 Abstract KoNA 用五类成对查询评选择性不遵从。KoNA 用来评测视觉语言模型能否对混合查询做选择性不遵从：只处理不该遵从的成分，同时回答其余成分。
审计视觉语言模型在敏感图像上从拒答转向国家立场重构的行为
Published Aug 12
Evaluated models Qwen2-VL-7B , Qwen2.5-VL-7B , Qwen3-VL-8B and others9 Abstract 论文系统审计了 VLM 多模态审查，发现审查正从显式拒答转向隐蔽重构，且中文提示与文本先验会放大重构倾向。论文系统研究了中外开源视觉语言模型在政治敏感图像上的审查行为，主要内容如下。
You have reached the end