AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

2025-10-17 至 2025-10-17 共收录 3 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 安全训练 3 篇

2510.14968 2025-10-17 cs.RO cs.AI cs.CV cs.LG cs.SY eess.SY 76%

RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks

Mingxuan Yan, Yuping Wang, Zechun Liu, Jiachen Li

机构 * University of California, Riverside（加州大学河滨分校）； University of Michigan（密歇根大学）； Meta AI

专题命中安全训练：alignment(title)；分类 cs.AI、cs.LG

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025); Project Website: rdd-neurips.github.io

2510.05179 2025-10-17 cs.CR cs.AI cs.LG 73%

Agentic Misalignment: How LLMs Could Be Insider Threats

Aengus Lynch, Benjamin Wright, Caleb Larson, Stuart J. Ritchie, Soren Mindermann, Evan Hubinger, Ethan Perez, Kevin Troy

机构 * University College London（伦敦大学学院）； Anthropic ； MATS ； Mila

专题命中安全训练：alignment(abstract)；safety(abstract)；分类 cs.AI、cs.LG

Comments 20 pages, 12 figures. Code available at https://github.com/anthropic-experimental/agentic-misalignment

2510.14276 2025-10-17 cs.CL 57%

Qwen3Guard Technical Report

Haiquan Zhao, Chenhan Yuan, Fei Huang, Xiaomeng Hu, Yichang Zhang, An Yang, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin, Baosong Yang, Chen Cheng, Jialong Tang, Jiandong Jiang, Jianwei Zhang, Jijie Xu, Ming Yan, Minmin Sun, Pei Zhang, Pengjun Xie, Qiaoyu Tang, Qin Zhu, Rong Zhang, Shibin Wu, Shuo Zhang, Tao He, Tianyi Tang, Tingyu Xia, Wei Liao, Weizhou Shen, Wenbiao Yin, Wenmeng Zhou, Wenyuan Yu, Xiaobin Wang, Xiaodong Deng, Xiaodong Xu, Xinyu Zhang, Yang Liu, Yeqiu Li, Yi Zhang, Yong Jiang, Yu Wan, Yuxin Zhou

机构 * Qwen Team（通义实验室）

专题命中安全训练：safety(abstract)；分类 cs.CL