大模型对齐与安全

P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis

Feifan Song, Bofei Gao, Yifan Song, Yi Liu, Weimin Xiong, Yuyang Song, Tianyu Liu, Guoyin Wang, Houfeng Wang

专题命中 偏好对齐 ：alignment(title,abstract)；分类 cs.CL、cs.AI

FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data

Thibaut Thonet, Germán Kruszewski, Jos Rozen, Pierre Erbacher, Marc Dymetman

机构 * NAVER Labs Europe（NAVER欧洲实验室） ； Independent Researcher（独立研究者） 纠错

专题命中 偏好对齐 ：alignment(title,abstract)；分类 cs.CL

CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning

Wenjie Li, Yujie Zhang, Haoran Sun, Yueqi Li, Fanrui Zhang, Mengzhe Xu, Victoria Borja Clausich, Sade Mellin, Renhao Yang, Chenrun Wang, Jethro Zih-Shuo Wang, Shiyi Yao, Gen Li, Yidong Xu, Hanyu Wang, Yilin Huang, Angela Lin Wang, Chen Shi, Yin Zhang, Jianan Guo, Luqi Yang, Renxuan Li, Yang Xu, Jiawei Liu, Yao Zhang, Lei Liu, Carlos Gutiérrez SanRomán, Lei Wang

机构 * College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院健康科学与技术学院） ； Shanghai Innovation Institute（上海创新研究院） ； Clinical Center for Sports Medicine, Department of Orthopaedics, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院骨科临床中心） ； School of Basic Medical Sciences, Intelligent Medicine Institute, Fudan University（复旦大学基础医学学院） ； Department of Hematology, The First Affiliated Hospital, College of Medicine, Zhejiang University（浙江大学医学院第一附属医院血液科） ； MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China（中国科学技术大学脑启发智能感知与认知教育部重点实验室） ； Department of Public Health and Primary Care, University of Cambridge（剑桥大学公共卫生与初级保健学院） ； Department of Medicine, Faculty of Health Sciences, Universidad CEU Cardenal Herrera（CEU卡德纳尔-赫尔曼大学健康科学学院医学系） ； Faculty of Medicine, University of Helsinki（赫尔辛基大学医学院） ； X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院X-LANCE实验室） ； Department of Hepatobiliary Surgery, National Cancer Center / National Clinical Research Center for Cancer / Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College（中国医学科学院肿瘤医院肝胆外科） ； Department of Surgery, The Ohio State University Wexner Medical Center, The James Comprehensive Cancer Center（俄亥俄州立大学韦克斯纳医学中心外科部，詹姆斯综合癌症中心） ； Ningbo Institute of Technology, Beihang University（北航宁波理工学院） 纠错

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

Are Today's LLMs Ready to Explain Well-Being Concepts?

Bohan Jiang, Dawei Li, Zhen Tan, Chengshuai Zhao, Huan Liu

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

Comments 9 pages, 4 figures, 3 tables

Real-World Offline Reinforcement Learning from Vision Language Model Feedback

Sreyas Venkataraman, Yufei Wang, Ziyu Wang, Navin Sriram Ravie, Zackory Erickson, David Held

机构 * Indian Institute of Technology, Kharagpur（印度理工学院，克哈格浦尔分校） ； IIIS, Tsinghua University（清华大学人工智能研究所） ； Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） 纠错

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

Comments 7 pages. Accepted at the LangRob Workshop 2024 @ CoRL, 2024. Accepted at 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)

Large Language Model's Multi-Capability Alignment in Biomedical Domain

Wentao Wu, Linqing Chen, Hanmeng Zhong, Weilei Wang

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

HarmonyGuard: Toward Safety and Utility in Web Agents via Adaptive Policy Enhancement and Dual-Objective Optimization

Yurun Chen, Xavier Hu, Yuhan Liu, Keting Yin, Juncheng Li, Zhuosheng Zhang, Shengyu Zhang

机构 * Zhejiang University（浙江大学） ； Xiamen University（厦门大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 安全训练 ：safety(title,abstract)；分类 cs.CL、cs.AI

The Emotional Baby Is Truly Deadly: Does your Multimodal Large Reasoning Model Have Emotional Flattery towards Humans?

Yuan Xun, Xiaojun Jia, Xinwei Liu, Hua Zhang

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； Nanyang Technological University（南洋理工大学） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

专题命中 安全训练 ：safety(abstract)；分类 cs.AI

Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application

Nys Tjade Siegel, James H. Cole, Mohamad Habes, Stefan Haufe, Kerstin Ritter, Marc-André Schulz

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

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations

Xiaohu Li, Yunfeng Ning, Zepeng Bao, Mayi Xu, Jianhao Chen, Tieyun Qian

机构 * School of Computer Science, Wuhan University, China（武汉大学计算机学院） ； Zhongguancun Academy, Beijing, China（中关村学院） 纠错

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

Comments Accepted to ACL 2025 (Findings), camera-ready version

Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models

Siddhant Panpatil, Hiskias Dingeto, Haon Park

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

Automatic LLM Red Teaming

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

专题命中 红队测试 ：red teaming(title,abstract)；分类 cs.AI、cs.LG

Towards Transparent AI Grading: Semantic Entropy as a Signal for Human-AI Disagreement

Karrtik Iyer, Manikandan Ravikiran, Prasanna Pendse, Shayan Mohanty

机构 * Thoughtworks AI Research Labs（Thoughtworks人工智能研究实验室） 纠错

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

Decoupled Contrastive Learning for Federated Learning

Hyungbin Kim, Incheol Baek, Yon Dohn Chung

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

T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion

Abdul Monaf Chowdhury, Rabeya Akter, Safaeid Hossain Arib

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

ChineseEEG-2: An EEG Dataset for Multimodal Semantic Alignment and Neural Decoding during Reading and Listening

Sitong Chen, Beiqianyi Li, Cuilin He, Dongyang Li, Mingyang Wu, Xinke Shen, Song Wang, Xuetao Wei, Xindi Wang, Haiyan Wu, Quanying Liu

专题命中 安全评测 ：alignment(title,abstract)

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Xiangzhe Xu, Guangyu Shen, Zian Su, Siyuan Cheng, Hanxi Guo, Lu Yan, Xuan Chen, Jiasheng Jiang, Xiaolong Jin, Chengpeng Wang, Zhuo Zhang, Xiangyu Zhang

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

Comments The first two authors (Xiangzhe Xu and Guangyu Shen) contributed equally to this work

Chain of Questions: Guiding Multimodal Curiosity in Language Models

Nima Iji, Kia Dashtipour

机构 * Edinburgh Napier University（爱丁堡纳皮尔大学） 纠错

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

Automated Generation of Curriculum-Aligned Multiple-Choice Questions for Malaysian Secondary Mathematics Using Generative AI

Rohaizah Abdul Wahid, Muhamad Said Nizamuddin Nadim, Suliana Sulaiman, Syahmi Akmal Shaharudin, Muhammad Danial Jupikil, Iqqwan Jasman Su Azlan Su

机构 * Fakulti Komputeran dan Meta-Teknologi (META), Universiti Pendidikan Sultan Idris（计算机与元技术学院（META），苏丹依德里斯教育大学） 纠错

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

"Think First, Verify Always": Training Humans to Face AI Risks

Yuksel Aydin

机构 * Independent Researcher（独立研究者） 纠错

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

FrEVL: Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding

Emmanuelle Bourigault, Pauline Bourigault

机构 * Department of Engineering Science, University of Oxford（牛津大学工程科学系） ； Department of Electrical Engineering, Imperial College London（伦敦帝国学院电子工程系） 纠错

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

Comments 8 pages, 4 figures

Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts

Millicent Ochieng, Anja Thieme, Ignatius Ezeani, Risa Ueno, Samuel Maina, Keshet Ronen, Javier Gonzalez, Jacki O'Neill

机构 * Microsoft Research（微软研究院） ； Lancaster University（兰卡斯特大学） ； University of Washington（华盛顿大学） 纠错

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

StepWrite: Adaptive Planning for Speech-Driven Text Generation

Hamza El Alaoui, Atieh Taheri, Yi-Hao Peng, Jeffrey P. Bigham

机构 * School of Computer Science Carnegie Mellon University Pittsburgh PA USA ； School of Computer Science Carnegie Mellon University 纠错

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

Comments This paper has been accepted to UIST 2025. For additional materials and project details, please see: https://www.cs.cmu.edu/~helalaou/publications/stepwrite

A Survey of Multimodal Ophthalmic Diagnostics: From Task-Specific Approaches to Foundational Models

Xiaoling Luo, Ruli Zheng, Qiaojian Zheng, Zibo Du, Shuo Yang, Meidan Ding, Qihao Xu, Chengliang Liu, Linlin Shen

机构 * College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China（深圳大学计算机科学与软件工程学院） ； Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology, Shenzhen, 518055, China（视觉对象检测与识别深圳重点实验室） ； Laboratory for Artificial Intelligence in Design, Hong Kong（人工智能设计实验室） ； School of Artificial Intelligence, Shenzhen University, Shenzhen, China（深圳大学人工智能学院） 纠错

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

Multimodal Video Emotion Recognition with Reliable Reasoning Priors

Zhepeng Wang, Yingjian Zhu, Guanghao Dong, Hongzhu Yi, Feng Chen, Xinming Wang, Jun Xie

机构 * Lenovo Research（联想研究院） ； School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院） ； Institute of Automation, CAS（中国科学院自动化研究所） ； Macau University of Science and Technology（澳门科学理工学院） ； School of Computer Science and Technology, UCAS（中国科学院大学计算机科学与技术学院） 纠错

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

Comments preprint

A Value Based Parallel Update MCTS Method for Multi-Agent Cooperative Decision Making of Connected and Automated Vehicles

Ye Han, Lijun Zhang, Dejian Meng, Zhuang Zhang, Xingyu Hu, Songyu Weng

机构 * School of Automotive Studies, Tongji University（同济大学汽车学院） 纠错

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments arXiv admin note: text overlap with arXiv:2408.04295 by other authors

A Survey of Controllable Learning: Methods and Applications in Information Retrieval

Chenglei Shen, Xiao Zhang, Teng Shi, Changshuo Zhang, Guofu Xie, Jun Xu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China, Beijing 100872, China（中国人民大学人工智能学院） ； AI Lab at Lenovo Research, Beijing 100085, China（联想研究院人工智能实验室） 纠错

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

TotalRegistrator: Towards a Lightweight Foundation Model for CT Image Registration

Xuan Loc Pham, Gwendolyn Vuurberg, Marjan Doppen, Joey Roosen, Tip Stille, Thi Quynh Ha, Thuy Duong Quach, Quoc Vu Dang, Manh Ha Luu, Ewoud J. Smit, Hong Son Mai, Mattias Heinrich, Bram van Ginneken, Mathias Prokop, Alessa Hering

机构 * Department of Imaging, Radboudumc, Nijmegen, the Netherlands（影像部，Radboudumc，尼姆egen，荷兰） ； Institute for Medical Informatics, University of Lübeck, Lübeck, Germany（医学信息研究所，吕贝克大学，吕贝克，德国） ； Department of Nuclear Medicine, Hospital 108, Hanoi, Vietnam（核医学部，108医院，河内，越南） ； Department of Diagnostic Imaging and Interventional Radiology, Thai Nguyen National Hospital, Thai Nguyen, Vietnam（诊断影像和介入放射科，Thai Nguyen国家医院，Thai Nguyen，越南） ； Interventional Radiology Center, Tam Anh Hospital, Hanoi, Vietnam（介入放射科中心，Tam Anh医院，河内，越南） ； FET, Vietnam National University, University of Engineering and Technology, Hanoi, Vietnam（FET，越南国家大学，工程与技术大学，河内，越南） 纠错

专题命中 安全评测 ：alignment(abstract)

Large Language Models Versus Static Code Analysis Tools: A Systematic Benchmark for Vulnerability Detection

Damian Gnieciak, Tomasz Szandala

专题命中 安全评测 ：safety(abstract)

CLIPVehicle: A Unified Framework for Vision-based Vehicle Search

Likai Wang, Ruize Han, Xiangqun Zhang, Wei Feng

机构 * College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学） ； Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院） ； Shenzhen University of Advanced Technology（深圳大学先进技术学院） 纠错

专题命中 安全评测 ：alignment(abstract)