大模型对齐与安全

Bridging Modality Gaps in e-Commerce Products via Vision-Language Alignment

Yipeng Zhang, Hongju Yu, Aritra Mandal, Canran Xu, Qunzhi Zhou, Zhe Wu

专题命中 偏好对齐 ：alignment(title,abstract)

REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations

Tianlong Yu, Lihong Liu, Ziyi Zhou, Fudu Xing, Kailong Wang, Yang Yang

机构 * School of Artificial Intelligence, Hubei University（湖北大学人工智能学院） ； Huazhong University of Science and Technology（华中科技大学） ； University of Southern California（美国南加州大学） 纠错

专题命中 偏好对齐 ：RLHF(abstract)；分类 cs.AI、cs.LG

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

Xinyu Wang, Jijun Chi, Zhenghan Tai, Tung Sum Thomas Kwok, Muzhi Li, Zhuhong Li, Hailin He, Yuchen Hua, Peng Lu, Suyuchen Wang, Yihong Wu, Jerry Huang, Jingrui Tian, Fengran Mo, Yufei Cui, Ling Zhou

机构 * 1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles 5The Chinese University of Hong Kong 6Duke University 7Universit\'e de Montr\'eal 8Mila - Quebec AI Institute 9Noah's Ark Lab 10CG Matrix Technology Limited ； 1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles ； 5The Chinese University of Hong Kong 6Duke University 7Universit\'e de Montr\'eal 8Mila - Quebec AI Institute ； 9Noah's Ark Lab 10CG Matrix Technology Limited 纠错

专题命中 偏好对齐 ：DPO(abstract)；分类 cs.AI、cs.LG

Comments Accepted at the 34th ACM International Conference on Information and Knowledge Management (CIKM2025)

Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7

Yuksel Aydin

机构 * Independent Researcher（独立研究者） 纠错

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

Making Qwen3 Think in Korean with Reinforcement Learning

Jungyup Lee, Jemin Kim, Sang Park, SeungJae Lee

机构 * Jungyup Lee, Jemin Kim, Sang Park, SeungJae Lee（作者） 纠错

专题命中 安全训练 ：alignment(abstract)；分类 cs.CL

Interpretable Machine Learning Model for Early Prediction of Acute Kidney Injury in Critically Ill Patients with Cirrhosis: A Retrospective Study

Li Sun, Shuheng Chen, Junyi Fan, Yong Si, Minoo Ahmadi, Elham Pishgar, Kamiar Alaei, Maryam Pishgar

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

A Semantic-Aware Framework for Safe and Intent-Integrative Assistance in Upper-Limb Exoskeletons

Yu Chen, Shu Miao, Chunyu Wu, Jingsong Mu, Bo OuYang, Xiang Li

机构 * Department of Automation, Tsinghua University（自动化系，清华大学） 纠错

专题命中 安全训练 ：safety(abstract)

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation

Zonglei Jing, Xiao Yang, Xiaoqian Li, Siyuan Liang, Aishan Liu, Mingchuan Zhang, Xianglong Liu

机构 * Beihang University（北航） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Taishan University（泰山大学） ； Nanyang Technological University（南洋理工大学） ； Henan University of Science and Technology（河南科技大学） 纠错

专题命中 安全训练 ：safety(abstract)

Traversability analysis with vision and terrain probing for safe legged robot navigation

Garen Haddeler, Meng Yee Michael Chuah, Yangwei You, Jianle Chan, Albertus H. Adiwahono, Wei Yun Yau, Chee-Meng Chew

专题命中 安全训练 ：safety(abstract)

Journal ref Frontiers in Robotics and AI, Volume 9 - 2022

The Cost of Thinking: Increased Jailbreak Risk in Large Language Models

Fan Yang

机构 * Fan Yang 纠错

专题命中 越狱攻击 ：jailbreak(title,abstract)；分类 cs.CL、cs.AI

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

Huizhen Shu, Xuying Li, Qirui Wang, Yuji Kosuga, Mengqiu Tian, Zhuo Li

专题命中 越狱攻击 ：alignment(abstract)；safety(abstract)；jailbreak(abstract)；分类 cs.CL、cs.AI

Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development

Sattvik Sahai, Prasoon Goyal, Michael Johnston, Anna Gottardi, Yao Lu, Lucy Hu, Luke Dai, Shaohua Liu, Samyuth Sagi, Hangjie Shi, Desheng Zhang, Lavina Vaz, Leslie Ball, Maureen Murray, Rahul Gupta, Shankar Ananthakrishna

机构 * Amazon（亚马逊） 纠错

专题命中 红队测试 ：alignment(abstract)；safety(abstract)；red teaming(abstract)；AI safety(abstract)

Comments 18 pages, 1st Proceedings of Amazon Nova AI Challenge (Trusted AI 2025)

An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs

Ayana Hussain, Patrick Zhao, Nicholas Vincent

专题命中 幻觉与事实性 ：jailbreak(abstract)；分类 cs.CL

Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesis

Xi Long, Christy Boscardin, Lauren A. Maggio, Joseph A. Costello, Ralph Gonzales, Rasmyah Hammoudeh, Ki Lai, Yoon Soo Park, Brian C. Gin

专题命中 幻觉与事实性 ：trustworthy(abstract)；分类 cs.AI

Chance-constrained Linear Quadratic Gaussian Games for Multi-robot Interaction under Uncertainty

Kai Ren, Giulio Salizzoni, Mustafa Emre Gürsoy, Maryam Kamgarpour

机构 * SYCAMORE Lab, École Polytechnique Fédérale de Lausanne (EPFL)（SYCAMORE实验室，瑞士联邦理工学院（EPFL）） 纠错

专题命中 幻觉与事实性 ：safety(abstract)

Comments Published in IEEE Control Systems Letters

Journal ref IEEE Control Systems Letters, vol. 9, pp. 2061-2066, 2025

FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models

Chuan Li, Qianyi Zhao, Fengran Mo, Cen Chen

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.AI

A Comprehensive Evaluation framework of Alignment Techniques for LLMs

Muneeza Azmat, Momin Abbas, Maysa Malfiza Garcia de Macedo, Marcelo Carpinette Grave, Luan Soares de Souza, Tiago Machado, Rogerio A de Paula, Raya Horesh, Yixin Chen, Heloisa Caroline de Souza Pereira Candello, Rebecka Nordenlow, Aminat Adebiyi

机构 * IBM Research（IBM研究院） 纠错

专题命中 安全评测 ：alignment(title,abstract)；RLHF(abstract)；safety(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments In submission

iSafetyBench: A video-language benchmark for safety in industrial environment

Raiyaan Abdullah, Yogesh Singh Rawat, Shruti Vyas

机构 * University of Central Florida（中央佛罗里达大学） 纠错

专题命中 安全评测 ：safety(title,abstract)

Comments Accepted to VISION'25 - ICCV 2025 workshop

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

PREF: Reference-Free Evaluation of Personalised Text Generation in LLMs

Xiao Fu, Hossein A. Rahmani, Bin Wu, Jerome Ramos, Emine Yilmaz, Aldo Lipani

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

Comments 7 pages

A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation

Jiulin Li, Ping Huang, Yexin Li, Shuo Chen, Juewen Hu, Ye Tian

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

Comments 8 pages, 5 figures

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

Runqi Qiao, Qiuna Tan, Peiqing Yang, Yanzi Wang, Xiaowan Wang, Enhui Wan, Sitong Zhou, Guanting Dong, Yuchen Zeng, Yida Xu, Jie Wang, Chong Sun, Chen Li, Honggang Zhang

机构 * BUPT（北京邮电大学） ； WeChat Vision, Tencent Inc.（腾讯公司） ； Tsinghua University（清华大学） 纠错

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

Comments Working in progress

Conformal P-Value in Multiple-Choice Question Answering Tasks with Provable Risk Control

Yuanchang Ye

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

An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach

Mohammad Amaz Uddin, Md Mahiuddin, Iqbal H. Sarker

机构 * Department of Computer Science and Engineering, BGC Trust University Bangladesh（Bangladesh BGC Trust 大学 计算机科学与工程系） ； Department of Computer Science and Engineering, International Islamic University Chittagong（Bangladesh 国际伊斯兰大学 昌德加荣分校 计算机科学与工程系） ； Centre for Securing Digital Futures, School of Science, Edith Cowan University（澳大利亚 埃德温·考文大学 科学学院 安全数字未来中心） 纠错

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

Medico 2025: Visual Question Answering for Gastrointestinal Imaging

Sushant Gautam, Vajira Thambawita, Michael Riegler, Pål Halvorsen, Steven Hicks

机构 * SimulaMet - Simula Metropolitan Center for Digital Engineering, Oslo, Norway（SimulaMet - Simula Metropolitan Center for Digital Engineering，挪威奥斯陆） ； Simula Research Laboratory, Oslo, Norway（Simula研究实验室，挪威奥斯陆） ； OsloMet - Oslo Metropolitan University, Oslo, Norway（OsloMet - 奥斯陆 Metropolitan 大学，挪威奥斯陆） 纠错

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

Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images

Solène Debuysère, Nicolas Trouvé, Nathan Letheule, Olivier Lévêque, Elise Colin

机构 * Paris-Saclay University（巴黎-萨克雷大学） ； ONERA - The French Aerospace Lab（法国航空航天实验室） 纠错

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

PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection

Haibin Sun, Xinghui Song

机构 * College of Computer Science and Engineering, Shandong University of Science and Technology（计算机科学与工程学院，山东科技大学） 纠错

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 11 pages, 6 figures

What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles

Mengtao Zhou, Sifan Wu, Huan Zhang, Qi Sima, Bang Liu

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

From Pixel to Mask: A Survey of Out-of-Distribution Segmentation

Wenjie Zhao, Jia Li, Yunhui Guo

机构 * University of Texas at Dallas（德克萨斯大学达拉斯分校） 纠错

专题命中 安全评测 ：safety(abstract)

Automated scoring of the Ambiguous Intentions Hostility Questionnaire using fine-tuned large language models

Y. Lyu, D. Combs, D. Neumann, Y. C. Leong

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

Comments We have no known conflict of interest