{"total":118,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"id":"2411.02193","title":"Improving Steering Vectors by Targeting Sparse Autoencoder Features","created":"2024-11-04","cited_by_count":92,"area":"mechinterp"},{"id":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71,"area":null},{"id":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","cited_by_count":64,"area":null},{"id":"2505.22637","title":"Understanding (Un)Reliability of Steering Vectors in Language Models","created":"2025-05-28","cited_by_count":47,"area":"mechinterp"},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2503.18878","title":"I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2505.14617","title":"The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2502.18862","title":"One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs","created":"2025-02-26","cited_by_count":29,"area":"mechinterp"},{"id":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2507.04742","title":"Activation Steering for Chain-of-Thought Compression","created":"2025-07-07","cited_by_count":24,"area":"lr"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2505.20809","title":"Improved Representation Steering for Language Models","created":"2025-05-27","cited_by_count":21,"area":"mechinterp"},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2502.13095","title":"Understanding and Rectifying Safety Perception Distortion in VLMs","created":"2025-02-18","cited_by_count":17,"area":"mllm"},{"id":"2505.18706","title":"Steering LLM Reasoning Through Bias-Only Adaptation","created":"2025-05-24","cited_by_count":16,"area":"lr"},{"id":"2508.10599","title":"Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models","created":"2025-08-14","cited_by_count":16,"area":"mechinterp"},{"id":"2502.02958","title":"Position: Editing Large Language Models Poses Serious Safety Risks","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2509.25175","title":"EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2602.01654","title":"Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models","created":"2026-02-02","cited_by_count":13,"area":"mechinterp"},{"id":"2505.12584","title":"Improving Multilingual Language Models by Aligning Representations through Steering","created":"2025-05-19","cited_by_count":11,"area":null},{"id":"2510.10157","title":"BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation","created":"2025-10-11","cited_by_count":11,"area":null},{"id":"2510.10205","title":"PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration","created":"2025-10-11","cited_by_count":11,"area":"mechinterp"},{"id":"2602.02343","title":"Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2602.03420","title":"CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering","created":"2026-02-03","cited_by_count":9,"area":"mechinterp"},{"id":"2505.20645","title":"STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2504.15133","title":"EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models","created":"2025-04-21","cited_by_count":7,"area":"mechinterp"},{"id":"2509.07983","title":"Steering Protein Language Models","created":"2025-07-01","cited_by_count":7,"area":null},{"id":"2510.22256","title":"SteerX: Disentangled Steering for LLM Personalization","created":"2025-10-25","cited_by_count":7,"area":"mechinterp"},{"id":"2601.22873","title":"EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis","created":"2026-01-30","cited_by_count":7,"area":"mechinterp"},{"id":"2604.08524","title":"What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal","created":"2026-04-09","cited_by_count":7,"area":"alignment"},{"id":"2507.13236","title":"Enhancing Cross-task Transfer of Large Language Models via Activation Steering","created":"2025-07-17","cited_by_count":6,"area":"mechinterp"},{"id":"2509.14814","title":"ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2510.02324","title":"Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning","created":"2025-09-25","cited_by_count":6,"area":"moe"},{"id":"2502.00653","title":"Towards Robust Multimodal Large Language Models Against Jailbreak Attacks","created":"2025-02-02","cited_by_count":5,"area":"safety"},{"id":"2505.15674","title":"UniErase: Towards Balanced and Precise Unlearning in Language Models","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2506.01301","title":"Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner","created":"2025-06-02","cited_by_count":5,"area":"lr"},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","cited_by_count":5,"area":"lr"},{"id":"2509.00373","title":"Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models","created":"2025-08-30","cited_by_count":5,"area":"mllm"},{"id":"2509.12934","title":"The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features","created":"2025-09-16","cited_by_count":5,"area":"alignment"},{"id":"2601.05062","title":"Compositional Steering of Large Language Models with Steering Tokens","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2602.07164","title":"Your Language Model Secretly Contains Personality Subnetworks","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2603.12298","title":"Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency","created":"2026-03-12","cited_by_count":5,"area":"mechinterp"},{"id":"2605.01844","title":"The Cylindrical Representation Hypothesis for Language Model Steering","created":"2026-05-03","cited_by_count":5,"area":null},{"id":"2505.12313","title":"ExpertSteer: Intervening in LLMs through Expert Knowledge","created":"2025-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2507.09508","title":"A Mixture of Linear Corrections Generates Secure Code","created":"2025-07-13","cited_by_count":4,"area":null},{"id":"2509.21884","title":"You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2602.07187","title":"PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents","created":"2026-02-06","cited_by_count":4,"area":"agents"},{"id":"2602.07639","title":"Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization","created":"2026-02-07","cited_by_count":4,"area":"alignment"},{"id":"2605.06076","title":"Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training","created":"2026-05-07","cited_by_count":4,"area":"mechinterp"},{"id":"2606.00460","title":"SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors","created":"2026-05-30","cited_by_count":4,"area":"mechinterp"},{"id":"2502.16385","title":"Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2507.08967","title":"Self-Improving Model Steering","created":"2025-07-11","cited_by_count":3,"area":"synth"},{"id":"2509.03647","title":"Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators","created":"2025-09-03","cited_by_count":3,"area":"alignment"},{"id":"2509.23982","title":"Toward Preference-aligned Large Language Models via Residual-based Model Steering","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2509.24169","title":"Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2601.06352","title":"CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation","created":"2026-01-09","cited_by_count":3,"area":"alignment"},{"id":"2603.02578","title":"How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2605.06342","title":"Don't Lose Focus: Activation Steering via Key-Orthogonal Projections","created":"2026-05-07","cited_by_count":3,"area":"mechinterp"},{"id":"2412.18497","title":"Neuron-Level Differentiation of Memorization and Generalization in Large Language Models","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2505.18562","title":"From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2508.14076","title":"PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement Learning","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2601.08441","title":"YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation","created":"2026-01-13","cited_by_count":2,"area":"alignment"},{"id":"2602.16930","title":"Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind Users","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2603.01792","title":"ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs","created":"2026-03-02","cited_by_count":2,"area":"safety"},{"id":"2604.05939","title":"Context-Value-Action Architecture for Value-Driven Large Language Model Agents","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2604.15488","title":"FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models","created":"2026-04-16","cited_by_count":2,"area":"mechinterp"},{"id":"2505.04260","title":"Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering","created":"2025-05-07","cited_by_count":1,"area":"mechinterp"},{"id":"2505.17132","title":"Dynamic Token Reweighting for Robust Vision-Language Models","created":"2025-05-22","cited_by_count":1,"area":"mllm"},{"id":"2509.25533","title":"VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models","created":"2025-09-29","cited_by_count":1,"area":"mllm"},{"id":"2604.00997","title":"Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2605.16362","title":"When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search","created":"2026-05-09","cited_by_count":1,"area":"mechinterp"},{"id":"2605.26612","title":"LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.01802","title":"On the Limits of Steering Vectors for Preference-Aligned Generation","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2608.12389","title":"Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2608.27338","title":"One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2609.19150","title":"Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2410.06225","title":"A Timeline and Analysis for Representation Plasticity in Large Language Models","created":"2024-10-08","cited_by_count":0,"area":"mechinterp"},{"id":"2508.08521","title":"VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models","created":"2025-08-11","cited_by_count":0,"area":"mllm"},{"id":"2509.25568","title":"Probing the Limits of Stylistic Alignment in Vision-Language Models","created":"2025-09-29","cited_by_count":0,"area":"mllm"},{"id":"2511.18933","title":"Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2512.12469","title":"Sparse Concept Anchoring for Interpretable and Controllable Neural Representations","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2601.07473","title":"AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.10339","title":"The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footage","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.01036","title":"Aligning Recommendations with User Popularity Preferences","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.20286","title":"Adaptive Probe-based Steering for Robust LLM Jailbreaking","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2605.23244","title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2605.28664","title":"Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection","created":"2026-05-27","cited_by_count":0,"area":"mechinterp"},{"id":"2606.03096","title":"Can Factual Opinions Be Edited (Manipulated) in Large Language Models?","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.23671","title":"Can LLMs Reliably Self-Report Adversarial Prefills, and How?","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":"100"}