大模型对齐与安全

Trustworthy Representation Learning via Information Funnels and Bottlenecks

João Machado de Freitas, Bernhard C. Geiger

机构 * Christian Doppler Laboratory for Dependable Intelligent Systems in Harsh Environments（可信智能系统在恶劣环境中的克里斯蒂安·多普勒实验室） ； Graz University of Technology（格拉茨技术大学） ； Know Center Research GmbH（Know Center研究有限责任公司） 纠错

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

Comments Published in Machine Learning (Springer), vol. 114, no. 12, Article 267, 2025

Journal ref Mach Learn 114, 267 (2025)

Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technology

Thomas Souverain

机构 * Department of AI Ethics, CEA Paris-Saclay（人工智能伦理系，CEA巴黎萨克雷） 纠错

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

Comments 17 pages, 2 Tables and 2 Pictures

The Mirror Loop: Recursive Non-Convergence in Generative Reasoning Systems

Bentley DeVilling

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

Comments 18 pages, 2 figures. Category: cs.LG. Code and data: https://github.com/Course-Correct-Labs/mirror-loop

No-Human in the Loop: Agentic Evaluation at Scale for Recommendation

Tao Zhang, Kehui Yao, Luyi Ma, Jiao Chen, Reza Yousefi Maragheh, Kai Zhao, Jianpeng Xu, Evren Korpeoglu, Sushant Kumar, Kannan Achan

机构 * Walmart Global Tech（沃尔玛全球技术） 纠错

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

Comments 4 page, NeurIPS 2025 Workshop: Evaluating the Evolving LLM Lifecycle

TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systems

Xiao Zhang, Qi Wang, Mingyi Li, Yuan Yuan, Mengbai Xiao, Fuzhen Zhuang, Dongxiao Yu

机构 * School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院） ； Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院） 纠错

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

Implementation Considerations for Automated AI Grading of Student Work

Zewei Tian, Alex Liu, Lief Esbenshade, Shawon Sarkar, Zachary Zhang, Kevin He, Min Sun

专题命中 安全评测 ：trustworthy(abstract)

SCALE-VLP: Soft-Weighted Contrastive Volumetric Vision-Language Pre-training with Spatial-Knowledge Semantics

Ailar Mahdizadeh, Puria Azadi Moghadam, Xiangteng He, Shahriar Mirabbasi, Panos Nasiopoulos, Leonid Sigal

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Vector Institute for AI（人工智能向量研究所） 纠错

专题命中 安全评测 ：alignment(abstract)