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。

2025-10-08 至 2025-10-08 共收录 44 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 安全评测 16 篇

2510.05142 2025-10-08 cs.CL cond-mat.mtrl-sci 57%

Reliable End-to-End Material Information Extraction from the Literature with Source-Tracked Multi-Stage Large Language Models

Xin Wang, Anshu Raj, Matthew Luebbe, Haiming Wen, Shuozhi Xu, Kun Lu

专题命中 安全评测 :trustworthy(abstract);分类 cs.CL

Comments 27 pages, 4 figures, 7 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04093 2025-10-08 cs.AI 57%

Harnessing LLM for Noise-Robust Cognitive Diagnosis in Web-Based Intelligent Education Systems

Guixian Zhang, Guan Yuan, Ziqi Xu, Yanmei Zhang, Jing Ren, Zhenyun Deng, Debo Cheng

机构 * School of Computer Science and Technology/School of Artificial Intelligence, China University of Mining and Technology(计算机科学与技术学院/人工智能学院,中国矿业大学) School of Computing Technologies, RMIT University(计算技术学院,拉筹伯大学) Department of Computer Science and Technology, University of Cambridge(计算机科学与技术系,剑桥大学) School of Computer Science and Technology, Hainan University(计算机科学与技术学院,海南大学)

专题命中 安全评测 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18427 2025-10-08 q-fin.CP q-fin.RM 50%

Tracing Positional Bias in Financial Decision-Making: Mechanistic Insights from Qwen2.5

Fabrizio Dimino, Krati Saxena, Bhaskarjit Sarmah, Stefano Pasquali

专题命中 安全评测 :trustworthy(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.00815 2025-10-08 econ.TH cs.GT math.OC 50%

Measurement of Trustworthiness of the Online Reviews

Dipankar Das

专题命中 安全评测 :trustworthy(abstract)

Comments This is a minor revision version and considers some intuitions related to applications. Moreover, a detailed algorithm has been added to facilitate a better understanding

详情

展开后加载摘要…

URL PDF HTML 收藏

2. AI治理与伦理 3 篇

2502.02444 2025-10-08 cs.CL cs.AI 73%

Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models

Haoran Ye, Tianze Zhang, Yuhang Xie, Liyuan Zhang, Yuanyi Ren, Xin Zhang, Guojie Song

机构 * State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(人工智能通用基础理论国家重点实验室,智能科学与技术学院,北京大学) Yuanpei College, Peking University(元培学院,北京大学) School of Psychological and Cognitive Sciences, Peking University(心理学与认知科学学院,北京大学) Key Laboratory of Machine Perception (Ministry of Education), Peking University(机器感知重点实验室(教育部),北京大学) PKU-Wuhan Institute for Artificial Intelligence(北京大学-武汉人工智能研究院)

专题命中 AI治理与伦理 :alignment(abstract);safety(abstract);分类 cs.CL、cs.AI

Comments ACL 2025 Main

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06105 2025-10-08 cs.AI cs.CY cs.HC cs.LG 67%

Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences

Batu El, James Zou

机构 * Stanford University(斯坦福大学)

专题命中 AI治理与伦理 :alignment(abstract);分类 cs.AI、cs.CY、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02563 2025-10-08 cs.LG cs.CL 62%

DynaGuard: A Dynamic Guardian Model With User-Defined Policies

Monte Hoover, Vatsal Baherwani, Neel Jain, Khalid Saifullah, Joseph Vincent, Chirag Jain, Melissa Kazemi Rad, C. Bayan Bruss, Ashwinee Panda, Tom Goldstein

机构 * University of Maryland(马里兰大学) Capital One

专题命中 AI治理与伦理 :safety(abstract);分类 cs.CL、cs.LG

Comments 22 Pages

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 其他安全 7 篇

2510.05184 2025-10-08 cs.AI 79%

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey

Jianglin Lu, Hailing Wang, Yi Xu, Yizhou Wang, Kuo Yang, Yun Fu

机构 * Department of Electrical and Computer Engineering, Northeastern University(东北大学电气与计算机工程系) Khoury College of Computer Science, Northeastern University(东北大学科赫里计算机科学学院)

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

Journal ref The 2025 Conference on Empirical Methods in Natural Language Processing

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08833 2025-10-08 cs.CY 79%

Position: The Pitfalls of Over-Alignment: Overly Caution Health-Related Responses From LLMs are Unethical and Dangerous

Wenqi Marshall Guo, Yiyang Du, Heidi J. S. Tworek, Shan Du

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05197 2025-10-08 cs.AI cs.LG stat.AP stat.ML 62%

Efficient Prediction of Pass@k Scaling in Large Language Models

Joshua Kazdan, Rylan Schaeffer, Youssef Allouah, Colin Sullivan, Kyssen Yu, Noam Levi, Sanmi Koyejo

机构 * Stanford University(斯坦福大学) University of Toronto(多伦多大学) EPFL(苏黎世联邦理工学院)

专题命中 其他安全 :safety(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05828 2025-10-08 cs.SD cs.CV cs.LG cs.MM eess.AS 57%

StereoSync: Spatially-Aware Stereo Audio Generation from Video

Christian Marinoni, Riccardo Fosco Gramaccioni, Kazuki Shimada, Takashi Shibuya, Yuki Mitsufuji, Danilo Comminiello

机构 * Sapienza University of Rome(罗马萨皮恩扎大学) Sony AI(索尼人工智能) Sony Group Corporation(索尼集团)

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

Comments Accepted at IJCNN 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05650 2025-10-08 cs.CV cs.CY 57%

EduVerse: A User-Defined Multi-Agent Simulation Space for Education Scenario

Yiping Ma, Shiyu Hu, Buyuan Zhu, Yipei Wang, Yaxuan Kang, Shiqing Liu, Kang Hao Cheong

机构 * Lab of Artificial Intelligence for Education(教育人工智能实验室) School of Physical and Mathematical Sciences(物理与数学科学学院) Institute of Automation(自动化研究所) Chinese Academy of Sciences(中国科学院) Department of Education(教育学院) College of Computing and Data Science(计算与数据科学学院)

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

Comments Preprint, Under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05985 2025-10-08 cs.RO 50%

AI-Enabled Capabilities to Facilitate Next-Generation Rover Surface Operations

Cristina Luna, Robert Field, Steven Kay

机构 * GMV Aerospace and Defence SAU(GMV航空航天与防御西班牙分公司) GMV NSL

专题命中 其他安全 :safety(abstract)

Comments Paper for 18th Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA), presented on October 7th at Leiden, Netherlands

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04193 2025-10-08 q-bio.QM 50%

Inverse statistics of active matter trajectories to distinguish interaction kernel anisotropy from emergent correlations

Simon F. Martina-Perez

专题命中 其他安全 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏