大模型对齐与安全

Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction

Sumanta Bhattacharyya, Sara Riazi, Pedram Rooshenas

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

MedicalOS: An LLM Agent based Operating System for Digital Healthcare

Jared Zhu, Junde Wu

机构 * University of Oxford（牛津大学） 纠错

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

GeoGPT-RAG Technical Report

Fei Huang, Fan Wu, Zeqing Zhang, Qihao Wang, Long Zhang, Grant Michael Boquet, Hongyang Chen

机构 * GeoGPT Team（GeoGPT团队） ； Zhejiang Lab（浙江实验室） 纠错

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

Comments 19 pages, 10 figures, 10 tables

Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework

David Herrera-Poyatos, Carlos Peláez-González, Cristina Zuheros, Virilo Tejedor, Rosana Montes, Francisco Herrera

机构 * Department of Computer Science and Artificial Intelligence（计算机科学与人工智能系） ； Andalusian Institute of Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所） ； University of Granada（格拉纳达大学） 纠错

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

Comments 27 pages, 9 tables and 2 figures

Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents

Rajesh Tembarai Krishnamachari, Srividya Rajesh

机构 * NYU（纽约大学） ； Independent Researcher（独立研究者） 纠错

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

MAD Chairs: A new tool to evaluate AI

Chris Santos-Lang

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

Comments 17 pages, 1 figure, reproduced with permission from Springer Nature from Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XVIII (COINE 2025)

LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis

Reza Fayyazi, Michael Zuzak, Shanchieh Jay Yang

机构 * Rochester Institute of Technology（罗切斯特技术学院） ； Gonzaga University（戈兹加大学） 纠错

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

Why Not Transform Chat Large Language Models to Non-English?

Xiang Geng, Ming Zhu, Jiahuan Li, Zhejian Lai, Wei Zou, Shuaijie She, Jiaxin Guo, Xiaofeng Zhao, Yinglu Li, Yuang Li, Chang Su, Yanqing Zhao, Xinglin Lyu, Min Zhang, Jiajun Chen, Hao Yang, Shujian Huang

机构 * National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China（新型软件技术国家重点实验室，南京大学，南京） ； Translation Services Center, Huawei Inc., Beijing 100085, China（翻译服务部，华为公司，北京） 纠错

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

Comments The article has been accepted by Frontiers of Computer Science (FCS), with the DOI: {10.1007/s11704-025-50646-z}

Graded Transformers

Tony Shaska

机构 * Department of Mathematics ； Statistics, Oakland University, Rochester, MI 48309 纠错

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

Safer Skin Lesion Classification with Global Class Activation Probability Map Evaluation and SafeML

Kuniko Paxton, Koorosh Aslansefat, Amila Akagić, Dhavalkumar Thakker, Yiannis Papadopoulos

机构 * School of Computer Science, University of Hull（赫尔大学计算机科学学院） ； Faculty of Electrical Engineering, University of Sarajevo（萨拉热窝大学电气工程学院） 纠错

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

Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol

Wei Ma, Yixiao Yang, Qiang Hu, Shi Ying, Zhi Jin, Bo Du, Zhenchang Xing, Tianlin Li, Junjie Shi, Yang Liu, Linxiao Jiang

机构 * Singapore Management University Singapore ； Capital Normal University Beijing China ； Tianjin University Tianjin China ； Wuhan University China ； CSIRO's Data61 \& Australian National University Australia ； Nanyang Technological University Singapore ； Singapore Management University ； Capital Normal University ； Tianjin University ； Wuhan University ； CSIRO's Data61 \& Australian National University ； Nanyang Technological University 纠错

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

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

Khaoula Chehbouni, Mohammed Haddou, Jackie Chi Kit Cheung, Golnoosh Farnadi

机构 * McGill University（麦吉尔大学） ； Mila - Quebec AI Institute（魁北克AI研究所） ； Statistics Canada（加拿大统计局） 纠错

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

Comments Prepared for conference submission

RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis

Anku Rani, Aparna Garimella, Apoorv Saxena, Balaji Vasan Srinivasan, Paul Pu Liang

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

MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers

Zhiqiang Wang, Yichao Gao, Yanting Wang, Suyuan Liu, Haifeng Sun, Haoran Cheng, Guanquan Shi, Haohua Du, Xiangyang Li

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

Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution

Zailong Tian, Zhuoheng Han, Yanzhe Chen, Haozhe Xu, Xi Yang, Richeng Xuan, Houfeng Wang, Lizi Liao

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

Categorical Construction of Logically Verifiable Neural Architectures

Logan Nye

机构 * Carnegie Mellon University School of Computer Science（卡内基梅隆大学计算机科学学院） 纠错

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

Agentic AI Frameworks: Architectures, Protocols, and Design Challenges

Hana Derouiche, Zaki Brahmi, Haithem Mazeni

机构 * University of Kairouan（卡鲁安大学） ； SMART Lab, University of Tunis（图纳大学SMART实验室） ； University of Sousse（索斯大学） ； Riadi Lab, Compus Manouba（曼努巴大学里亚迪实验室） ； University of Jandouba（贾杜巴大学） 纠错

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

Generative AI-Driven High-Fidelity Human Motion Simulation

Hari Iyer, Neel Macwan, Atharva Jitendra Hude, Heejin Jeong, Shenghan Guo

机构 * The Polytechnic School, Ira A. Fulton Schools of Engineering, Arizona State University（亚利桑那州立大学工程学院Polytechnic学院） ； School of Manufacturing Systems and Networks, Ira A. Fulton Schools of Engineering, Arizona State University（亚利桑那州立大学工程学院制造系统与网络学院） 纠错

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

eSapiens: A Platform for Secure and Auditable Retrieval-Augmented Generation

Isaac Shi, Zeyuan Li, Fan Liu, Wenli Wang, Lewei He, Yang Yang, Tianyu Shi

机构 * eSapiens Team（eSapiens团队） 纠错

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

GAF-Guard: An Agentic Framework for Risk Management and Governance in Large Language Models

Seshu Tirupathi, Dhaval Salwala, Elizabeth Daly, Inge Vejsbjerg

机构 * IBM Research Europe（IBM欧洲研究院） 纠错

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

Public Service Algorithm: towards a transparent, explainable, and scalable content curation for news content based on editorial values

Ahmad Mel, Sebastien Noir

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

Journal ref IAMCR 2025 Conference

Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate

Mikel K. Ngueajio, Flor Miriam Plaza-del-Arco, Yi-Ling Chung, Danda B. Rawat, Amanda Cercas Curry

机构 * Howard University（霍华德大学） ； LIACS, Leiden University（莱顿大学LIACS） ； Genaios（基因奥斯） ； CENTAI Institute（CENTAI研究院） 纠错

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.AI、cs.CY

Comments Accepted at ACL WOAH 2025

Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values

Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, Xing Xie

机构 * Microsoft Research Asia（微软亚洲研究院） ； Fudan University（复旦大学） ； Tsinghua University（清华大学） ； The University of Chicago（芝加哥大学） ； Renmin University of China（中国人民大学） ； William & Mary（威廉与玛丽大学） 纠错

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

SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents

Kunlun Zhu, Jiaxun Zhang, Ziheng Qi, Nuoxing Shang, Zijia Liu, Peixuan Han, Yue Su, Haofei Yu, Jiaxuan You

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

AI-Supported Platform for System Monitoring and Decision-Making in Nuclear Waste Management with Large Language Models

Dongjune Chang, Sola Kim, Young Soo Park

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

Journal ref Proceedings of the WM2025 Conference, March 9-13, 2025, Phoenix, Arizona, USA

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models

Baihui Zheng, Boren Zheng, Kerui Cao, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

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

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun

机构 * Singapore Management University（新加坡管理大学） ； The University of Melbourne（墨尔本大学） ； Fudan University（复旦大学） 纠错

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

Comments 22 pages

Generative AI and the problem of existential risk

Lynette Webb

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

Comments arXiv admin comment: This version has been removed by arXiv administrators as the submitter did not have the rights to agree to the license at the time of submission

An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-training

Yuxiang Nie, Sunan He, Yequan Bie, Yihui Wang, Zhixuan Chen, Shu Yang, Zhiyuan Cai, Hongmei Wang, Xi Wang, Luyang Luo, Mingxiang Wu, Xian Wu, Ronald Cheong Kin Chan, Yuk Ming Lau, Yefeng Zheng, Pranav Rajpurkar, Hao Chen

机构 * Shenzhen People’s Hospital（深圳人民医院） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

ControlNET: A Firewall for RAG-based LLM System

Hongwei Yao, Haoran Shi, Yidou Chen, Yixin Jiang, Cong Wang, Zhan Qin

专题命中 安全评测 ：prompt injection(abstract)；harmlessness(abstract)；分类 cs.LG

Comments Project Page: https://ai.zjuicsr.cn/firewall