大模型对齐与安全

The Impact of Coreset Selection on Spurious Correlations and Group Robustness

Amaya Dharmasiri, William Yang, Polina Kirichenko, Lydia Liu, Olga Russakovsky

机构 * Princeton University（普林斯顿大学） ； FAIR at Meta（Meta 的 FAIR 实验室） 纠错

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

Comments 10 pages, 9 additional pages for Appendix

The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability

Zijie Xu, Minfeng Qi, Shiqing Wu, Lefeng Zhang, Qiwen Wei, Han He, Ningran Li

专题命中 安全评测 ：safety(abstract)

Evaluating LLM-Based Mobile App Recommendations: An Empirical Study

Quim Motger, Xavier Franch, Vincenzo Gervasi, Jordi Marco

专题命中 安全评测 ：alignment(abstract)

Comments Under review

Hearing Health in Home Healthcare: Leveraging LLMs for Illness Scoring and ALMs for Vocal Biomarker Extraction

Yu-Wen Chen, William Ho, Sasha M. Vergez, Grace Flaherty, Pallavi Gupta, Zhihong Zhang, Maryam Zolnoori, Margaret V. McDonald, Maxim Topaz, Zoran Kostic, Julia Hirschberg

机构 * The Fu Foundation School of Engineering and Applied Science, Columbia University（哥伦比亚大学福基金会工程与应用科学学院） ； School of Nursing, Columbia University（哥伦比亚大学护理学院） ； Center for Home Care Policy & Research, VNS Health（VNS健康居家护理政策与研究中心） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments The Second Workshop on GenAI for Health at NeurIPS 2025

3D Audio-Visual Segmentation

Artem Sokolov, Swapnil Bhosale, Xiatian Zhu

机构 * University of Surrey, UK（Surrey大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted at the NeurIPS 2024 Workshop on Audio Imagination; this version updates the project page link

Building Trust in Clinical LLMs: Bias Analysis and Dataset Transparency

Svetlana Maslenkova, Clement Christophe, Marco AF Pimentel, Tathagata Raha, Muhammad Umar Salman, Ahmed Al Mahrooqi, Avani Gupta, Shadab Khan, Ronnie Rajan, Praveenkumar Kanithi

机构 * M42, Abu Dhabi（阿布扎比M42） 纠错

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

Comments Accepted to EMNLP Main 2025

Vibe Coding: Toward an AI-Native Paradigm for Semantic and Intent-Driven Programming

Vinay Bamil

专题命中 AI治理与伦理 ：alignment(abstract)

Comments 10 pages, 1 figure, 2 tables

Annotating the Chain-of-Thought: A Behavior-Labeled Dataset for AI Safety

Antonio-Gabriel Chacón Menke, Phan Xuan Tan, Eiji Kamioka

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

Combining Cost-Constrained Runtime Monitors for AI Safety

Tim Tian Hua, James Baskerville, Henri Lemoine, Mia Hopman, Aryan Bhatt, Tyler Tracy

机构 * MARS ； Redwood Research 纠错

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

Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage

Ángela López-Cardona, Sebastián Idesis, Mireia Masias-Bruns, Sergi Abadal, Ioannis Arapakis

机构 * Universitat Politècnica de Catalunya（加泰罗尼亚理工大学） 纠错

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

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable

Ruoxin Chen, Junwei Xi, Zhiyuan Yan, Ke-Yue Zhang, Shuang Wu, Jingyi Xie, Xu Chen, Lei Xu, Isabel Guan, Taiping Yao, Shouhong Ding

机构 * Tencent YouTu Lab（腾讯优图实验室） ； East China University of Science and Technology（东华大学） ； Peking University（北京大学） ； Renmin University of China（中国人民大学） ； Shenzhen University（深圳大学） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

专题命中 其他安全 ：alignment(title,abstract)

Comments NeurIPS 2025 Spotlight. 13 Pages, 10 figures

Zero-Shot Vehicle Model Recognition via Text-Based Retrieval-Augmented Generation

Wei-Chia Chang, Yan-Ann Chen

机构 * Yuan Ze University（元智大学） 纠错

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

Comments Accepted by The 38th Conference of Open Innovations Association FRUCT, 2025

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, Xiaowei Huang

机构 * School of Computer Science and Informatics, University of Liverpool, UK（计算机科学与信息学学院，利物浦大学） 纠错

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

Comments Accepted at NeurIPS 2025 with minor revisions

Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting

Taha Binhuraib, Greta Tuckute, Nicholas Blauch

机构 * Novus Technologies ； MIT（麻省理工学院） ； Harvard University（哈佛大学） 纠错

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

Comments ICLR 2024 Workshop on Representational Alignment (Re-Align) Camera Ready

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder

Yongmin Lee, Hye Won Chung

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

Comments NeurIPS 2025

Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval

Yubai Wei, Jiale Han, Yi Yang

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

Comments Link: https://github.com/BaileyWei/BMEmbed

Journal ref Findings of the Association for Computational Linguistics ACL 2025

Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models

Tsogt-Ochir Enkhbayar

机构 * Mongol AI（蒙古AI） 纠错

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

Comments 12 pages, 3 figures, 4 tables

Investigating the Impact of Dark Patterns on LLM-Based Web Agents

Devin Ersoy, Brandon Lee, Ananth Shreekumar, Arjun Arunasalam, Muhammad Ibrahim, Antonio Bianchi, Z. Berkay Celik

专题命中 其他安全 ：safety(abstract)

Comments At IEEE S&P 2026