{"total":323,"rows":[{"id":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91,"area":null},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","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":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"area":null},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2410.13722","title":"Persistent Pre-Training Poisoning of LLMs","created":"2024-10-17","cited_by_count":48,"area":null},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48,"area":null},{"id":"2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","created":"2025-05-19","cited_by_count":41,"area":null},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2505.17306","title":"Refusal Direction is Universal Across Safety-Aligned Languages","created":"2025-05-22","cited_by_count":38,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"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":"2505.24535","title":"Beyond Linear Steering: Unified Multi-Attribute Control for Language Models","created":"2025-05-30","cited_by_count":25,"area":null},{"id":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2602.07852","title":"Emergent Misalignment is Easy, Narrow Misalignment is Hard","created":"2026-02-08","cited_by_count":23,"area":null},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2505.20546","title":"Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline","created":"2025-05-26","cited_by_count":21,"area":null},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2506.00085","title":"COSMIC: Generalized Refusal Direction Identification in LLM Activations","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2506.08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin","created":"2025-06-10","cited_by_count":19,"area":null},{"id":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2412.11965","title":"Inferring Functionality of Attention Heads from their Parameters","created":"2024-12-16","cited_by_count":17,"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":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14,"area":null},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2506.24068","title":"STACK: Adversarial Attacks on LLM Safeguard Pipelines","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2501.08145","title":"Refusal Behavior in Large Language Models: A Nonlinear Perspective","created":"2025-01-14","cited_by_count":13,"area":null},{"id":"2503.01751","title":"SAKE: Steering Activations for Knowledge Editing","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2509.22449","title":"Detecting (Un)answerability in Large Language Models with Linear Directions","created":"2025-09-26","cited_by_count":13,"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":"2504.02904","title":"How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence","created":"2025-04-03","cited_by_count":12,"area":null},{"id":"2509.13281","title":"RepIt: Steering Language Models with Concept-Specific Refusal Vectors","created":"2025-09-16","cited_by_count":12,"area":null},{"id":"2602.15669","title":"PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2505.11770","title":"Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2505.12584","title":"Improving Multilingual Language Models by Aligning Representations through Steering","created":"2025-05-19","cited_by_count":11,"area":null},{"id":"2505.22586","title":"Precise In-Parameter Concept Erasure in Large Language Models","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2508.17158","title":"Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks","created":"2025-08-23","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2505.18215","title":"Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?","created":"2025-05-23","cited_by_count":10,"area":null},{"id":"2603.22161","title":"Causal Evidence that Language Models use Confidence to Drive Behavior","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2604.19117","title":"LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit","created":"2026-04-21","cited_by_count":10,"area":null},{"id":"2503.17755","title":"Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes","created":"2025-03-22","cited_by_count":9,"area":null},{"id":"2503.23306","title":"Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts","created":"2025-03-30","cited_by_count":9,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2512.17639","title":"Linear Personality Probing and Steering in LLMs: A Big Five Study","created":"2025-12-19","cited_by_count":9,"area":null},{"id":"2412.13341","title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","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":"2510.05969","title":"Probing the Difficulty Perception Mechanism of Large Language Models","created":"2025-10-07","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":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2410.06704","title":"PII-Scope: A Comprehensive Study on Training Data PII Extraction Attacks in LLMs","created":"2024-10-09","cited_by_count":7,"area":null},{"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":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2507.21141","title":"The Geometry of Harmfulness in LLMs through Subconcept Probing","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2508.10003","title":"Semantic Structure in Large Language Model Embeddings","created":"2025-08-04","cited_by_count":7,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2606.17056","title":"The Value Axis: Language Models Encode Whether They're on the Right Track","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2410.22517","title":"Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2502.12055","title":"Designing Role Vectors to Improve LLM Inference Behaviour","created":"2025-02-17","cited_by_count":6,"area":null},{"id":"2505.16170","title":"When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2506.12217","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models","created":"2025-06-13","cited_by_count":6,"area":null},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.02768","title":"A Granular Study of Safety Pretraining under Model Abliteration","created":"2025-10-03","cited_by_count":6,"area":null},{"id":"2601.19375","title":"Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection","created":"2026-01-27","cited_by_count":6,"area":null},{"id":"2602.10161","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2602.11079","title":"Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2603.03308","title":"Old Habits Die Hard: How Conversational History Geometrically Traps LLMs","created":"2026-02-08","cited_by_count":6,"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":"2504.06303","title":"On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2507.22623","title":"Multilingual Political Views of Large Language Models: Identification and Steering","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2410.22370","title":"Survey of User Interface Design and Interaction Techniques in Generative AI Applications","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2502.15507","title":"Steering LLMs for Formal Theorem Proving","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2504.03933","title":"Language Models Are Implicitly Continuous","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2505.21800","title":"From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2506.17052","title":"From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2507.00322","title":"Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2509.19372","title":"Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.01238","title":"Silent Tokens, Loud Effects: Padding in LLMs","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2604.07382","title":"Latent Structure of Affective Representations in Large Language Models","created":"2026-04-08","cited_by_count":4,"area":null}],"next_cursor":"100"}