While defenses for structured PII are mature, Large Language Models (LLMs) pose a new threat: Semantic Sensitive Information (SemSI), where models infer sensitive identity attributes, generate reputation-harmful content, or hallucinate potentially wrong information. The capacity of LLMs to self-regulate these complex, context-dependent sensitive information leaks without destroying utility remains an open scientific question. To address this, we introduce SemSIEdit, an inference-time framework where an agentic "Editor" iteratively critiques and rewrites sensitive spans to preserve narrative flow rather than simply refusing to answer. Our analysis reveals a Privacy-Utility Pareto Frontier, where this agentic rewriting reduces leakage by 34.6% across all three SemSI categories while incurring a marginal utility loss of 9.8%. We also uncover a Scale-Dependent Safety Divergence: large reasoning models (e.g., GPT-5) achieve safety through constructive expansion (adding nuance), whereas capacity-constrained models revert to destructive truncation (deleting text). Finally, we identify a Reasoning Paradox: while inference-time reasoning increases baseline risk by enabling the model to make deeper sensitive inferences, it simultaneously empowers the defense to execute safe rewrites.
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
University of Science and Technology of China(中国科学技术大学);Hefei University of Technology(合肥工业大学);The Hong Kong University of Science and Technology(香港科学与技术大学);Institute of Intelligent Machines, Chinese Academy of Sciences(中国科学院智能 Machines 研究所)
From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails
Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所);Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电气与计算机工程系);Equal Advising(平等指导)
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
State Key Laboratory of Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院);AMAP, Alibaba Group(阿里集团AMAP)
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
Zhejiang University(浙江大学);Hong Kong Polytechnic University(香港理工大学);East China Normal University(华东师范大学);Southern University of Science and Technology(南方科技大学);Renmin University(中国人民大学);Nanyang Technological University(南洋理工大学);Xiaohongshu Inc.(小红书公司);INSAIT
Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?
Department of Engineering, University of Cambridge(剑桥大学工程系);Department of Informatics, King’s College London(伦敦大学国王学院信息学院);SCB 10X, SCBX Group(SCB 10X,SCBX集团)
Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
Parameter Lab(参数实验室);Data and Web Science Group(数据与网络科学小组);University of Mannheim(曼海姆大学);UKP Lab(UKP实验室);Technical University of Darmstadt(达姆施塔特技术大学);NAVER AI Lab(NAVER人工智能实验室);University of Tübingen(图宾根大学);Tübingen AI Center(图宾根人工智能中心)
Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院)
ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
College of Computing and Data Science, Nanyang Technological University, Singapore(计算与数据科学学院,南洋理工大学,新加坡);Alibaba(阿里巴巴);School of Computer Science, Peking University, China(计算机科学学院,北京大学,中国)
From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task
Faculty of Exact and Natural Sciences, University of Buenos Aires(布宜诺斯艾利斯大学精确与自然科学学院);National Scientific and Technical Research Council (CONICET)(国家科学技术研究委员会(CONICET))
Probing the contents of semantic representations from text, behavior, and brain data using the psychNorms metabase
Faculty of Psychology, University of Basel(巴塞尔大学心理学系);Center for Adaptive Rationality, Max Planck Institute for Human Development(马克斯·普朗克人类发展研究所适应性理性中心);School of Psychology, UNSW(新南威尔士大学心理学学院)