FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering
University of Electronic Science and Technology of China(电子科技大学);Mohamed bin Zayed University of Artificial Intelligence(马尔代夫人工智能大学);South China University of Technology(华南理工大学)
Zikang Ding, Qiying Hu, Yi Zhang, Hongji Li, Junchi Yao, Hongbo Liu, Lijie Hu
Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce targeted behavioral changes. However, such conclusions are typically drawn under relatively relaxed evaluation settings that overlook deployment constraints, capability trade-offs, and real-world robustness. We therefore introduce \textbf{FaithSteer-BENCH}, a stress-testing benchmark that evaluates steering methods at a fixed deployment-style operating point through three gate-wise criteria: controllability, utility preservation, and robustness. Across multiple models and representative steering approaches, we uncover several systematic failure modes that are largely obscured under standard evaluation, including illusory controllability, measurable cognitive tax on unrelated capabilities, and substantial brittleness under mild instruction-level perturbations, role prompts, encoding transformations, and data scarcity. Gate-wise benchmark results show that existing methods do not necessarily provide reliable controllability in deployment-oriented practical settings. In addition, mechanism-level diagnostics indicate that many steering methods induce prompt-conditional alignment rather than stable latent directional shifts, further explaining their fragility under stress. FaithSteer-BENCH therefore provides a unified benchmark and a clearer analytical lens for future method design, reliability evaluation, and deployment-oriented research in steering.
ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Northwestern University(西北大学);William & Mary(威廉与玛丽学院);University of Washington(华盛顿大学);Stanford University(斯坦福大学)
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Rutgers University(罗格斯大学);South China Agricultural University(华南农业大学);Columbia University(哥伦比亚大学);Fenz.AI;QuantaAlpha;Adobe;Santa Clara University(圣克拉拉大学);City University of Hong Kong(香港城市大学)
VIS Lab, University of Amsterdam(阿姆斯特丹大学VIS实验室);FunAI Lab, University of Technology Nuremberg(纽伦堡技术大学FunAI实验室);CSAIL, Massachusetts Institute of Technology(麻省理工学院计算机科学与人工智能实验室)
Latent space bias directions in LLMs capture confidence, not fairness
Institute of Astronomy & Kavli Institute for Cosmology, University of Cambridge(剑桥大学天文学研究所及卡夫利宇宙学研究所);Risk and Security AI Lab, Visa Inc.(Visa公司风险与安全人工智能实验室)
Mitigating Entangled Steering in Large Vision-Language Models for Hallucination Reduction
Ministry of Education Key Laboratory of Intelligent Networks and Network Security(教育部智能网络与网络安全重点实验室);Centre for Frontier AI Research, Institute of High Performance Computing, Agency for Science, Technology and Research(前沿人工智能研究中心,高性能计算研究所,科技研究局)
CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology(华中科技大学国家大数据技术与系统工程技术研究中心、服务计算技术与系统实验室、集群与网格计算实验室);Singapore Management University(新加坡管理大学)
SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Nanjing University of Aeronautics and Astronautics(南京航空航天大学);The 63rd Research Institute, National University of Defense Technology, Nanjing(国防科技大学第六三研究所,南京)
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室);School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);Peking University School of Software and Microelectronics(北京大学软件与微电子学院);Peking University School of Psychological and Cognitive Sciences(北京大学心理与认知科学学院);Key Laboratory of Machine Perception (Ministry of Education), Peking University(北京大学机器感知重点实验室)