{"total":143,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"id":"2502.15603","title":"Do Multilingual LLMs Think In English?","created":"2025-02-21","cited_by_count":78,"area":"lr"},{"id":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"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":"2410.17245","title":"Towards Reliable Evaluation of Behavior Steering Interventions in LLMs","created":"2024-10-22","cited_by_count":36,"area":"mechinterp"},{"id":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"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":"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":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"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":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2511.04847","title":"Test-Time Adaptation for LLM Agents via Environment Interaction","created":"2025-11-06","cited_by_count":20,"area":"agents"},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2411.08790","title":"Can sparse autoencoders be used to decompose and interpret steering vectors?","created":"2024-11-13","cited_by_count":19,"area":"mechinterp"},{"id":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"area":null},{"id":"2604.03147","title":"Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control","created":"2026-04-03","cited_by_count":16,"area":null},{"id":"2511.06626","title":"Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"id":"2411.07213","title":"Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks","created":"2024-11-11","cited_by_count":14,"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":"2606.00995","title":"Subliminal Learning Is Steering Vector Distillation","created":"2026-05-31","cited_by_count":13,"area":"mechinterp"},{"id":"2508.12535","title":"CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features","created":"2025-08-18","cited_by_count":12,"area":"mechinterp"},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2603.09313","title":"Curveball Steering: The Right Direction To Steer Isn't Always Linear","created":"2026-03-10","cited_by_count":11,"area":"mechinterp"},{"id":"2507.08218","title":"Simple Mechanistic Explanations for Out-Of-Context Reasoning","created":"2025-07-10","cited_by_count":10,"area":"lr"},{"id":"2509.23799","title":"Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement","created":"2025-09-28","cited_by_count":10,"area":"mechinterp"},{"id":"2603.24543","title":"Analysing the Safety Pitfalls of Steering Vectors","created":"2026-03-25","cited_by_count":10,"area":"safety"},{"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":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","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":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2604.09839","title":"Steered LLM Activations are Non-Surjective","created":"2026-04-10","cited_by_count":8,"area":"mechinterp"},{"id":"2506.00653","title":"Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2510.08506","title":"Neologism Learning for Controllability and Self-Verbalization","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2511.18284","title":"What Can We Actually Steer? A Multi-Behavior Study of Activation Control","created":"2025-11-23","cited_by_count":6,"area":"mechinterp"},{"id":"2603.02237","title":"Concept Heterogeneity-aware Representation Steering","created":"2026-02-13","cited_by_count":6,"area":"mechinterp"},{"id":"2604.02608","title":"Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens","created":"2026-04-03","cited_by_count":6,"area":"mechinterp"},{"id":"2605.10664","title":"Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions","created":"2026-05-11","cited_by_count":6,"area":"mechinterp"},{"id":"2411.07965","title":"SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs","created":"2024-11-12","cited_by_count":5,"area":null},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"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":"2511.03738","title":"Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs","created":"2025-10-29","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":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2606.02211","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","created":"2026-06-01","cited_by_count":4,"area":null},{"id":"2606.06333","title":"Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability","created":"2026-06-04","cited_by_count":4,"area":"mechinterp"},{"id":"2606.11893","title":"Beyond representational alignment with brain-guided language models for robust reasoning","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2606.22357","title":"ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation","created":"2026-06-21","cited_by_count":4,"area":"mechinterp"},{"id":"2505.01162","title":"On the Limitations of Steering in Language Model Alignment","created":"2025-05-02","cited_by_count":3,"area":"alignment"},{"id":"2505.03189","title":"Patterns and Mechanisms of Contrastive Activation Engineering","created":"2025-05-06","cited_by_count":3,"area":"mechinterp"},{"id":"2505.17760","title":"But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2505.24208","title":"Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap","created":"2025-05-30","cited_by_count":3,"area":"mllm"},{"id":"2509.22510","title":"We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2510.08734","title":"Transmuting prompts into weights","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2602.02712","title":"Towards Understanding Steering Strength","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2604.03867","title":"Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment","created":"2026-04-04","cited_by_count":3,"area":"alignment"},{"id":"2606.04775","title":"Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control","created":"2026-06-03","cited_by_count":3,"area":"mechinterp"},{"id":"2606.14388","title":"A Low-Rank Subspace Analysis of LLM Interventions","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2509.15759","title":"On Optimal Steering to Achieve Exact Fairness","created":"2025-09-19","cited_by_count":2,"area":"mechinterp"},{"id":"2605.09760","title":"ConFit v3: Improving Resume-Job Matching with LLM-based Re-Ranking","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.12765","title":"Inference-Time Machine Unlearning via Gated Activation Redirection","created":"2026-05-12","cited_by_count":2,"area":"safety"},{"id":"2606.00033","title":"Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing","created":"2026-04-24","cited_by_count":2,"area":"mechinterp"},{"id":"2606.08682","title":"Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation","created":"2026-06-07","cited_by_count":2,"area":"mechinterp"},{"id":"2606.11205","title":"Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention","created":"2026-04-22","cited_by_count":2,"area":"mechinterp"},{"id":"2606.30449","title":"Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring","created":"2026-06-29","cited_by_count":2,"area":"agents"},{"id":"2607.10517","title":"Conditional Optimal Bridge for Riemannian Activation Steering","created":"2026-07-12","cited_by_count":2,"area":"mechinterp"},{"id":"2608.19338","title":"Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability","created":"2026-08-19","cited_by_count":2,"area":"mechinterp"},{"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":"2510.09790","title":"Mapping Semantic & Syntactic Relationships with Geometric Rotation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.24772","title":"Confidence is Not Competence","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.00158","title":"RAPTOR: Ridge-Adaptive Logistic Probes","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.02595","title":"To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack","created":"2026-02-01","cited_by_count":1,"area":"safety"},{"id":"2602.06440","title":"TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2604.06377","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2606.02528","title":"Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.29034","title":"The strength of clinical evidence is recoverable from language model representations but not from their stated grades","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.20469","title":"DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions","created":"2026-05-21","cited_by_count":1,"area":"inference"},{"id":"2607.23458","title":"Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2607.24645","title":"Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects","created":"2026-07-27","cited_by_count":1,"area":"mechinterp"},{"id":"2608.00023","title":"Role Steering of Language Models for Social Simulations","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2608.05732","title":"CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits","created":"2026-08-06","cited_by_count":1,"area":"mechinterp"},{"id":"2608.22985","title":"What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces","created":"2026-08-24","cited_by_count":1,"area":"mechinterp"},{"id":"2608.24335","title":"SteerCheck: Attribution Specificity and Alignment Leakage in Activation-Steering Audits","created":"2026-08-25","cited_by_count":1,"area":"mechinterp"},{"id":"2609.05800","title":"Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment","created":"2026-09-05","cited_by_count":1,"area":"alignment"},{"id":"2609.16247","title":"The Pain Axis: LLMs Represent Self-Directed Harm and Act on It","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2609.22135","title":"Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models","created":"2026-08-24","cited_by_count":1,"area":"mechinterp"},{"id":"2505.19313","title":"Concept Reachability in Diffusion Models: Beyond Dataset Constraints","created":"2025-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2507.05235","title":"Logit Reweighting for Topic-Focused Summarization","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"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":"2512.12469","title":"Sparse Concept Anchoring for Interpretable and Controllable Neural Representations","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.18551","title":"Neologism Learning as a Parameter-Efficient Alternative to Fine-Tuning for Model Steering","created":"2025-12-21","cited_by_count":0,"area":null}],"next_cursor":"100"}