arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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。

2025-09-19 至 2025-09-19 共收录 7 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 7 篇

2509.10685 2025-09-19 cs.CL cs.AI cs.LG 82%

Pluralistic Alignment for Healthcare: A Role-Driven Framework

Jiayou Zhong, Anudeex Shetty, Chao Jia, Xuanrui Lin, Usman Naseem

机构 * Cheriton School of Computer Science, University of Waterloo(滑铁卢大学计算机科学学院) School of Computing, FSE, Macquarie University(麦觉大学计算机学院) School of Computing and Information System, the University of Melbourne(墨尔本大学计算机与信息系统学院) Rajax Network Technology (ele.me), China(中国Rajax网络技术(饿了么)) Alibaba Cloud Computing, Alibaba Group, China(中国阿里云 computing,阿里集团)

专题命中 其他安全 :alignment(title,abstract);分类 cs.CL、cs.AI、cs.LG

Comments Accepted to EMNLP 2025 (Main Proceedings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14735 2025-09-19 cs.CL 79%

Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM

Chenkun Tan, Pengyu Wang, Shaojun Zhou, Botian Jiang, Zhaowei Li, Dong Zhang, Xinghao Wang, Yaqian Zhou, Xipeng Qiu

机构 * Fudan University(复旦大学)

专题命中 其他安全 :alignment(title,abstract);分类 cs.CL

Comments Accepted by Findings of EMNLP2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14738 2025-09-19 cs.CL 57%

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets

Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu

机构 * Fudan University(复旦大学)

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments Accepted by Findings of EMNLP2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14554 2025-09-19 cs.CY 57%

Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation

Xiaoming Zhai

专题命中 其他安全 :alignment(abstract);分类 cs.CY

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21830 2025-09-19 cs.AI 57%

DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework

Kuiye Ding, Fanda Fan, Yao Wang, Ruijie jian, Xiaorui Wang, Luqi Gong, Yishan Jiang, Chunjie Luo, Jianfeng Zhan

机构 * SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences(处理器国家重点实验室,计算技术研究所,中国科学院) Fu Foundation School of Engineering and Applied Science, Columbia University(工程与应用科学学院,哥伦比亚大学) University of Chinese Academy of Sciences(中国科学院大学) Zhejiang Lab(浙江实验室) Beijing University of Technology(北京理工大学) Institute of Computing Technology, Chinese Academy of Sciences(计算技术研究所,中国科学院)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

Comments This paper has been accepted by ACM Multimedia 2025 (ACM MM 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.15703 2025-09-19 cs.MA cs.AI 57%

Predicting Multi-Agent Specialization via Task Parallelizability

Elizabeth Mieczkowski, Ruaridh Mon-Williams, Neil Bramley, Christopher G. Lucas, Natalia Velez, Thomas L. Griffiths

机构 * Princeton University(普林斯顿大学) University of Edinburgh(爱丁堡大学)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.16724 2025-09-19 cs.SD eess.AS 50%

SALM: Spatial Audio Language Model with Structured Embeddings for Understanding and Editing

Jinbo Hu, Yin Cao, Ming Wu, Zhenbo Luo, Jun Yang

机构 * Institute of Acoustics, Chinese Academy of Sciences, China(中国科学院声学研究所) MiLM Plus, Xiaomi Inc., China(小米公司) Xi’an Jiaotong Liverpool University, China(西安交通大学利物浦大学) University of Chinese Academy of Sciences, China(中国科学院大学)

专题命中 其他安全 :alignment(abstract)

Comments 5 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏