Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 17 papers Another 233 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.
用 SafeEvo 提取拒绝电路，并提出 SCA 仅微调该电路
Published Oct 7
Evaluated models Llama-3-8B , Qwen-2.5-7B , Mistral-7B-v0.1 and others4 Abstract SafeEvo 识别出基座模型中存在的弱安全电路及其演化动态，据此提出的 SCA 算法实现了安全对齐、能力保留与低过度拒绝的平衡。
提出 SOUL 稀疏特征策略遗忘，缓解 VLA 状态幻觉
Published Oct 7
Evaluated models OpenVLA , π0.5 Abstract SOUL 以稀疏特征遗忘 VLA 状态幻觉。SOUL 用稀疏特征引导的策略 unlearning 处理 VLA 的 state hallucination。
提出分风险对齐标度律框架，测量各类风险的对齐负担如何随规模变化
Published Oct 6
Evaluated models Pythia (14m–2.8b) , Qwen2.5 (0.5B–72B) , Qwen2.5-Instruct (0.5B–14B) and others4 Abstract 论文提出了分风险对齐标度律框架，测得真实性与倾向纠错呈标度有益，但盲后门仍存活，揭示隐藏风险的长期挑战。本文提出了一个将大语言模型对齐难度形式化为可测量标度关系的理论框架与预注册评测协议。
提出 ASCENT，在效用微调中做一阶安全校准并只压制负贡献更新
Published Oct 6
Evaluated models Qwen2.5-7B-Instruct , Llama-3.1-8B-Instruct , Gemma-3-12B-it and others4 提出融合定位拒答与能力保留的安全微调，补齐视觉定位输出的拒答缺口
Published Oct 5
Evaluated models Claude Sonnet 4.6 , Gemini 3.5 Flash , Molmo2-8B and others5 Abstract 论文揭示了 VLM 定位安全落后于 VQA 的对齐断层，提出三成分微调方案有效弥合差距并保留定位能力，表征分析揭示了对齐机制。
用持续更新的探针做微调，降低有害性并保持线性可监测性
Published Sep 30
Evaluated models Mistral 7B Instruct v0.1 , Llama 3 8B Instruct Abliterated , Qwen3-14B Abstract 持续重拟合的探针可降低有害性、提高诚实性，训练后概念仍能被线性探针读出。Probe-guided fine-tuning 把探针分数当作唯一对齐信号，用来推动 harmlessness 与 honesty，并检查训练后这些概念是否仍线性可读。
提出 Intent-Privilege OPSD，对齐视觉语言模型在隐式风险下的安全与帮助性
Published Sep 29
Evaluated models Qwen3-VL-4B-Instruct , LLaVA , LLaVA-1.5-7B and others4 Abstract 作者报告训练期证据化意图蒸馏兼顾安全与帮助性，效果受标注质量和评测设置影响。Intent-Privilege OPSD 是针对跨模态隐式风险的训练期安全—帮助性对齐方法。 作者关注的不是直接拒绝敏感请求，而是按可观察图文证据保留正常帮助、约束有害信息。
提出 SURE 三阶段框架，用韩语对抗提示与安全打分做 SFT 与 DPO
Published Sep 29
Evaluated models KULLM3-10.7B , Qwen-2-7B , Llama-3-8B 提出 ORPG，协调多奖励目标的策略梯度更新
Published Sep 28 Abstract ORPG 按梯度夹角与任务优先级调和两个裁剪策略目标，并在对齐和数学推理上比较联合表现。ORPG 是一种多奖励策略梯度调和方法：每个奖励保持独立裁剪目标，相容时协调贡献幅度，冲突时按任务优先级投影。
提出 DeShortcut-Align，解耦伪捷径以增强推理模型安全对齐
Published Sep 28 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。
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 分析良性知识蒸馏中提示模板对学生拒答保留的影响
Published Sep 25
Evaluated models LLaMA-3.1-8B-Instruct , LLaMA-3.2-3B-Instruct , Gemma-2-9B-IT and others6 Proposes Rationale-Only safety fine-tuning, removing the refusal statement to reduce false refusals.
Published Sep 4
Evaluated models Llama-3.1-8B , Mistral-7B-v0.3 , Gemma-2-9B and others8 Abstract Removing the boilerplate refusal statement and training only on the rationale can reduce false refusals, while the compliance rate on harmful queries remains low.This is a structural analysis of safety fine-tuning data: false refusals are traced by the authors to formulaic refusal statements in responses, rather than relying only on inference-time remedies.
提出 WIFA 意图组监督微调，缓解包装式越狱与过度拒答
Published Aug 13
Evaluated models Qwen2.5-7B-Instruct , Llama-3.1-8B-Instruct Abstract WIFA 用匹配意图组做数据层，WIFA-Boost 偏高安全，A-GCRT 在 Qwen 上把过拒降到基座以下。WIFA 是一种自动意图组数据构造，用来让安全微调拒绝有害意图而不是拒绝表面包装。WIFA-Boost 与 A-GCRT 在同一数据层上选取不同的安全–过拒工作点。
提出 DataShield，用共识子空间过滤会削弱安全的微调数据
Published Jul 16
Evaluated models Phi3-medium-4k-it , Qwen3-4B-it , Gemma2-27B-it and others4 提出 ShaPO，只在安全关键子空间做最坏情况偏好对齐
Published Feb 7
Evaluated models Pythia-2.8B , LLaMA-3.2-3B , LLaMA-3-8B and others4 You have reached the end