大模型对齐与安全

AI Alignment vs. AI Ethical Treatment: 10 Challenges

Adam Bradley, Bradford Saad

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

Comments author order is arbitrary

Emotional Cognitive Modeling Framework with Desire-Driven Objective Optimization for LLM-empowered Agent in Social Simulation

Qun Ma, Xiao Xue, Xuwen Zhang, Zihan Zhao, Yuwei Guo, Ming Zhang

机构 * College of Intelligence and Computing（智能与计算学院） ； Faculty of Environment, Science and Economy（环境、科学与经济学院） 纠错

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

Towards Region-aware Bias Evaluation Metrics

Angana Borah, Aparna Garimella, Rada Mihalcea

机构 * University of Michigan（密歇根大学） ； Adobe Research（Adobe研究） 纠错

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

Comments Accepted to Cross-Cultural Considerations in NLP (C3NLP Workshop at NAACL 2025) -- Outstanding Paper Award

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

Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module

Ruitao Feng, Bixi Zhang, Sheng Liang, Zheng Yuan

机构 * The University of Hong Kong, Fauclty of Science, Hong Kong（香港大学科学学院） ； Aix-Marseille University, Laboratoire Parole et Langage (LPL), France（艾克斯-马赛大学语言与言语实验室（LPL）） 纠错

专题命中 其他安全 ：alignment(title,abstract)

Comments 5 pages, 1 figures. Code is available at: https://github.com/forfrt/SteerMoE. Submitted to ICASSP 2026

OS-HGAdapter: Open Semantic Hypergraph Adapter for Large Language Models Assisted Entropy-Enhanced Image-Text Alignment

Rongjun Chen, Chengsi Yao, Jinchang Ren, Xianxian Zeng, Peixian Wang, Jun Yuan, Jiawen Li, Huimin Zhao, Xu Lu

机构 * School of Computer Science, Guangdong Polytechnic Normal University（广东 polytechnic 正规大学计算机学院） 纠错

专题命中 其他安全 ：alignment(title,abstract)

Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers

Xin Zhao, Xiaojun Chen, Bingshan Liu, Haoyu Gao, Zhendong Zhao, Yilong Chen

专题命中 其他安全 ：safety(abstract)；AI safety(abstract)

Aligning Large Language Models to Low-Resource Languages through LLM-Based Selective Translation: A Systematic Study

Rakesh Paul, Anusha Kamath, Kanishk Singla, Raviraj Joshi, Utkarsh Vaidya, Sanjay Singh Chauhan, Niranjan Wartikar

机构 * NVIDIA 纠错

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

From Narratives to Probabilistic Reasoning: Predicting and Interpreting Drivers' Hazardous Actions in Crashes Using Large Language Model

Boyou Chen, Gerui Xu, Zifei Wang, Huizhong Guo, Ananna Ahmed, Zhaonan Sun, Zhen Hu, Kaihan Zhang, Shan Bao

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

Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain

Jingmin An, Yilong Song, Ruolin Yang, Nai Ding, Lingxi Lu, Yuxuan Wang, Wei Wang, Chu Zhuang, Qian Wang, Fang Fang

机构 * Peking University（北京大学） ； Zhejiang University（浙江大学） ； Beijing Language and Culture University（北京语言大学） ； Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院） 纠错

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

3-Model Speculative Decoding

Sanghyun Byun, Mohanad Odema, Jung Ick Guack, Baisub Lee, Jacob Song, Woo Seong Chung

机构 * LG Electronics USA（LG电子美国公司） 纠错

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

Comments Accepted at NeurIPS SPIGM 2025

InferA: A Smart Assistant for Cosmological Ensemble Data

Justin Z. Tam, Pascal Grosset, Divya Banesh, Nesar Ramachandra, Terece L. Turton, James Ahrens

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

OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning

Alexandre Oliveira, Katarina Dyreby, Francisco Caldas, Cláudia Soares

机构 * NOVA LINCS 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Adaptive Visual Conditioning for Semantic Consistency in Diffusion-Based Story Continuation

Seyed Mohammad Mousavi, Morteza Analoui

机构 * School of Computer Engineering, Iran University of Science and Technology（伊朗科学技术大学计算机工程学院） 纠错

专题命中 其他安全 ：alignment(abstract)

EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection

Huaizhi Qu, Ruichen Zhang, Shuqing Luo, Luchao Qi, Zhihao Zhang, Xiaoming Liu, Roni Sengupta, Tianlong Chen

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Michigan State University（密歇根州立大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Visual Interestingness Decoded: How GPT-4o Mirrors Human Interests

Fitim Abdullahu, Helmut Grabner

机构 * Zurich University of Applied Sciences（苏黎世应用科学大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments ICCV 2025

EPIPTrack: Rethinking Prompt Modeling with Explicit and Implicit Prompts for Multi-Object Tracking

Yukuan Zhang, Jiarui Zhao, Shangqing Nie, Jin Kuang, Shengsheng Wang

机构 * College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院） ； Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University（吉林大学教育部长春符号计算与知识工程重点实验室） ； Yangtze University（扬子大学） 纠错

专题命中 其他安全 ：alignment(abstract)

State-Change Learning for Prediction of Future Events in Endoscopic Videos

Saurav Sharma, Chinedu Innocent Nwoye, Didier Mutter, Nicolas Padoy

机构 * University of Strasbourg, CNRS, INSERM, ICube, UMR7357, France（斯特拉斯堡大学，法国国家科学研究中心，法国国家医学研究院，ICube，UMR7357，法国） ； University Hospital of Strasbourg, France（斯特拉斯堡大学医院，法国） 纠错

专题命中 其他安全 ：safety(abstract)

Comments 24 pages, 13 figures

Data-Efficient Fine-Tuning of Vision-Language Models for Diagnosis of Alzheimer's Disease

Fangqi Cheng, Surajit Ray, Xiaochen Yang

机构 * School of Mathematics and Statistics, University of Glasgow, UK（数学与统计学学院，格拉斯哥大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments Accepted at MICAD 2025

A Machine Learning Tool to Analyse Spectroscopic Changes in High-Dimensional Data

Alberto Martinez-Serra, Gionni Marchetti, Francesco D'Amico, Ivana Fenoglio, Barbara Rossi, Marco P. Monopoli, Giancarlo Franzese

专题命中 其他安全 ：safety(abstract)

Comments 32 pages, 9 figures, added references, revised manuscript, results unchanged, Journal reference added

Journal ref International Journal of Biological Macromolecules 330 148095 (2025)

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent

Xinyao Liao, Xianfang Zeng, Liao Wang, Gang Yu, Guosheng Lin, Chi Zhang

机构 * Nanyang Technological University（南洋理工大学） ； StepFun ； Westlake University（西湖大学） 纠错

专题命中 其他安全 ：alignment(abstract)