大模型对齐与安全

Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TS

Liangwei Nathan Zheng, Wenhao Liang, Wei Emma Zhang, Miao Xu, Olaf Maennel, Weitong Chen

机构 * The University of Adelaide（阿德莱德大学） ； The University of Queensland（昆士兰大学） 纠错

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

Fine-grained Analysis of Brain-LLM Alignment through Input Attribution

Michela Proietti, Roberto Capobianco, Mariya Toneva

机构 * Sapienza University of Rome（罗马萨皮恩扎大学） ； Sony AI（索尼人工智能） ； Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所） 纠错

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

SeeingSounds: Learning Audio-to-Visual Alignment via Text

Simone Carnemolla, Matteo Pennisi, Chiara Russo, Simone Palazzo, Daniela Giordano, Concetto Spampinato

机构 * University of Catania（卡塔尼亚大学） 纠错

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

Comments accepted to ACM Multimedia Asia 2025

When Openness Fails: Lessons from System Safety for Assessing Openness in AI

Tamara Paris, Shalaleh Rismani

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

Comments Accepted to Symposium on Model Accountability, Sustainability and Healthcare (SMASH) 2025

On the Entity-Level Alignment in Crosslingual Consistency

Yihong Liu, Mingyang Wang, François Yvon, Hinrich Schütze

机构 * Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML）） ； Sorbonne Université, CNRS, ISIR, France（索邦大学，CNRS，ISIR，法国） 纠错

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

Comments preprint

Text-Based Approaches to Item Alignment to Content Standards in Large-Scale Reading & Writing Tests

Yanbin Fu, Hong Jiao, Tianyi Zhou, Nan Zhang, Ming Li, Qingshu Xu, Sydney Peters, Robert W. Lissitz

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

Comments need updates

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） 纠错

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

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

Spectral Alignment as Predictor of Loss Explosion in Neural Network Training

Haiquan Qiu, You Wu, Yingjie Tan, Yaqing Wang, Quanming Yao

机构 * Tsinghua University（清华大学） ； Beijing Institute of Mathematical Sciences and Applications（北京数学科学研究院） 纠错

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

Comments 18 pages, 8 figures

Automating construction safety inspections using a multi-modal vision-language RAG framework

Chenxin Wang, Elyas Asadi Shamsabadi, Zhaohui Chen, Luming Shen, Alireza Ahmadian Fard Fini, Daniel Dias-da-Costa

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

Comments 33 pages, 11 figures, 7 tables

To Mask or to Mirror: Human-AI Alignment in Collective Reasoning

Crystal Qian, Aaron Parisi, Clémentine Bouleau, Vivian Tsai, Maël Lebreton, Lucas Dixon

机构 * Google DeepMind（谷歌DeepMind） ； Paris School of Economics（巴黎经济学院） 纠错

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

Taxonomy of Comprehensive Safety for Clinical Agents

Jean Seo, Hyunkyung Lee, Gibaeg Kim, Wooseok Han, Jaehyo Yoo, Seungseop Lim, Kihun Shin, Eunho Yang

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

Comments EMNLP 2025 Industry

Enabling Rapid Shared Human-AI Mental Model Alignment via the After-Action Review

Edward Gu, Ho Chit Siu, Melanie Platt, Isabelle Hurley, Jaime Peña, Rohan Paleja

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

Comments Accepted to the Cooperative Multi-Agent Systems Decision-making and Learning:Human-Multi-Agent Cognitive Fusion Workshop at AAAI 2025

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment

Mengyu Bu, Shaolei Zhang, Zhongjun He, Hua Wu, Yang Feng

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（智能信息处理重点实验室，计算技术研究所，中国科学院） ； Key Laboratory of AI Safety, Chinese Academy of Sciences（人工智能安全重点实验室，中国科学院） ； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国） ； Baidu Inc.（百度公司） 纠错

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

Comments Accepted to EMNLP 2025 Main Conference. The code will be available at https://github.com/ictnlp/AlignX

Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation

Yuanfei Wang, Xinju Huang, Fangwei Zhong, Yaodong Yang, Yizhou Wang, Yuanpei Chen, Hao Dong

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

Distillation-Enabled Knowledge Alignment Protocol for Semantic Communication in AI Agent Networks

Jingzhi Hu, Geoffrey Ye Li

机构 * Department of Electrical and Electronic Engineering, Imperial College London（帝国理工学院伦敦分校电子与电气工程系） 纠错

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

Comments Code available at https://github.com/DJ-Duke/DeKAP

Journal ref IEEE Communications Letters, early access, Aug. 2025

Embodied Representation Alignment with Mirror Neurons

Wentao Zhu, Zhining Zhang, Yuwei Ren, Yin Huang, Hao Xu, Yizhou Wang

机构 * Center on Frontiers of Computing Studies, School of Compter Science, Peking University（前沿计算研究中心，计算机科学学院，北京大学） ； Eastern Institute of Technology, Ningbo（宁波技术研究所） ； Qualcomm AI Research（高通人工智能研究） ； Inst. for Artificial Intelligence, Peking University（人工智能研究所，北京大学） 纠错

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

Comments ICCV 2025

PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs

Pei Zhang, Andong Chen, Xi Chen, Baosong Yang, Derek F. Wong, Fei Huang

机构 * Tongyi Lab, Alibaba Group（通义实验室，阿里巴巴集团） ； The Chinese University of Hong Kong（香港中文大学） ； NLP 2 CT Lab, University of Macau（自然语言处理2CT实验室，澳门大学） 纠错

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

How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment

Julie Jung, Max Lu, Sina Chole Benker, Dogus Darici

机构 * Harvard Graduate School of Education（哈佛教育研究生院） ； Munster University（穆恩斯特大学） ； Institute of Anatomy and Neurobiology, University of Münster（解剖与神经生物学研究所，穆恩斯特大学） 纠错

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

Comments 9 pages, 4 figures, accepted at NCME AIME 2025

Embedding Alignment in Code Generation for Audio

Sam Kouteili, Hiren Madhu, George Typaldos, Mark Santolucito

机构 * Yale University（耶鲁大学） ； Columbia University（哥伦比亚大学） 纠错

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

Comments Accepted to NeurIPS 2025 AI4Music Workshop

Dynamical Alignment: A Principle for Adaptive Neural Computation

Xia Chen

机构 * Georg Nemetschek Institute Munich Data Science Institute（慕尼黑数据科学研究所） ； Technische Universität München（慕尼黑技术大学） 纠错

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

Comments 16 pages, 10 figures;

OmniBridge: Unified Multimodal Understanding, Generation, and Retrieval via Latent Space Alignment

Teng Xiao, Zuchao Li, Lefei Zhang

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） 纠错

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

Align Where the Words Look: Cross-Attention-Guided Patch Alignment with Contrastive and Transport Regularization for Bengali Captioning

Riad Ahmed Anonto, Sardar Md. Saffat Zabin, M. Saifur Rahman

机构 * Bangladesh University of Engineering and Technology (BUET)（孟加拉工程与技术大学） 纠错

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

Can multimodal representation learning by alignment preserve modality-specific information?

Romain Thoreau, Jessie Levillain, Dawa Derksen

机构 * institutetext（机构文本） ； CNES（法国国家空间研究中心） ； INSA-IMT（法国里尔INSA-IMT） 纠错

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

Comments Accepted as a workshop paper at MACLEAN - ECML/PKDD 2025

Informative Text-Image Alignment for Visual Affordance Learning with Foundation Models

Qian Zhang, Lin Zhang, Xing Fang, Mingxin Zhang, Zhiyuan Wei, Ran Song, Wei Zhang

机构 * School of Control Science and Engineering, Shandong University（控制科学与工程学院，山东大学） 纠错

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

Comments Submitted to the IEEE International Conference on Robotics and Automation (ICRA) 2026

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） 纠错

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

Comments Accepted by Findings of EMNLP2025

Consistent View Alignment Improves Foundation Models for 3D Medical Image Segmentation

Puru Vaish, Felix Meister, Tobias Heimann, Christoph Brune, Jelmer M. Wolterink

机构 * Department of Applied Mathematics, Technical Medical Centre, University of Twente（代尔夫特理工大学应用数学系） ； Digital Technology and Innovation, Siemens Healthineers, Erlangen, Germany（西门子医疗创新部，埃尔朗根，德国） 纠错

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

Comments MICCAI 2025: 1st Place in Transformer track and 2nd Place in Convolution track of SSL3D-OpenMind challenge

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification

Jikai Wang, Zhenxu Tian, Juntao Li, Qingrong Xia, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Min Zhang

机构 * Soochow University（苏州大学） ； Key Laboratory of Data Intelligence and Advanced Computing, Soochow University（数据智能与先进计算关键实验室） ； Huawei Cloud（华为云） 纠错

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

Comments Accepted at EMNLP 2025 Main

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems

Minghang Zhu, Zhengliang Shi, Zhiwei Xu, Shiguang Wu, Lingjie Wang, Pengjie Ren, Zhaochun Ren, Zhumin Chen

机构 * Shandong University（山东大学） ； Leiden University（莱顿大学） 纠错

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

Comments EMNLP 2025 Findings

Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment

Sascha Kaltenpoth, Oliver Müller

机构 * Paderborn University, Department of Business Administration and Economics（帕德博恩大学商业管理与经济学系） 纠错

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

Comments Presented at the 19th International Conference on Wirtschaftsinformatik 2024, Würzburg, Germany https://aisel.aisnet.org/wi2024/91/