model steering

AI Steerability 360: A Toolkit for Steering Large Language Models ACL 2026 Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models CVPR 2026 Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026 Interpretable and Steerable Concept Bottleneck Sparse Autoencoders CVPR 2026 Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions EACL 2026 Analyzing Finetuning Representation Shift for Multimodal LLMs Steering ICCV 2025 Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders EMNLP 2025 Can Language Neuron Intervention Reduce Non-Target Language Output? EMNLP 2025 Can We Talk Models Into Seeing the World Differently? ICLR 2025 CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models ACL 2025 Controlling Large Language Models Through Concept Activation Vectors AAAI 2025 Do Transformer Interpretability Methods Transfer to RNNs? AAAI 2025 EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models EMNLP 2025 Exploring Chain-of-Thought Reasoning for Steerable Pluralistic Alignment EMNLP 2025 Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models EMNLP 2025 Improving Instruction-Following in Language Models through Activation Steering ICLR 2025 Interpretable Generative Models through Post-hoc Concept Bottlenecks CVPR 2025 Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations EMNLP 2025 Linear Representations of Political Perspective Emerge in Large Language Models ICLR 2025 LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates ACL 2025 Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws ICML 2025 Multi-Attribute Steering of Language Models via Targeted Intervention ACL 2025 Multilingual Political Views of Large Language Models: Identification and Steering IJCNLP 2025 Probe-Free Low-Rank Activation Intervention NAACL 2025 Proxy Tuning for Financial Sentiment Analysis: Overcoming Data Scarcity and Computational Barriers COLING 2025