{"total":68,"rows":[{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032,"area":"safety"},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2403.00745","title":"AtP*: An efficient and scalable method for localizing LLM behaviour to components","created":"2024-03-01","cited_by_count":111,"area":"mechinterp"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77,"area":"mechinterp"},{"id":"2406.15518","title":"Steering Without Side Effects: Improving Post-Deployment Control of Language Models","created":"2024-06-21","cited_by_count":46,"area":"safety"},{"id":"2405.19358","title":"Robustifying Safety-Aligned Large Language Models through Clean Data Curation","created":"2024-05-24","cited_by_count":44,"area":"alignment"},{"id":"2403.05767","title":"Extending Activation Steering to Broad Skills and Multiple Behaviours","created":"2024-03-09","cited_by_count":40,"area":"mechinterp"},{"id":"2410.16314","title":"Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering","created":"2024-10-09","cited_by_count":39,"area":"mechinterp"},{"id":"2502.11356","title":"SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models","created":"2025-02-17","cited_by_count":34,"area":"mechinterp"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29,"area":"agents"},{"id":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","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":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2410.00153","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","created":"2024-09-30","cited_by_count":27,"area":null},{"id":"2503.03730","title":"Towards Understanding Distilled Reasoning Models: A Representational Approach","created":"2025-03-05","cited_by_count":26,"area":"lr"},{"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":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2405.04160","title":"A Causal Explainable Guardrails for Large Language Models","created":"2024-05-07","cited_by_count":18,"area":"safety"},{"id":"2501.11041","title":"Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach","created":"2025-01-19","cited_by_count":14,"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":"2504.14640","title":"Risk Assessment Framework for Code LLMs via Leveraging Internal States","created":"2025-04-20","cited_by_count":9,"area":null},{"id":"2505.15038","title":"Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering","created":"2025-05-21","cited_by_count":9,"area":"mechinterp"},{"id":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"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":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"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":"2601.04765","title":"Differential syntactic and semantic encoding in LLMs","created":"2026-01-08","cited_by_count":7,"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":"2506.02996","title":"Linear Spatial World Models Emerge in Large Language Models","created":"2025-06-03","cited_by_count":6,"area":"wm"},{"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":"2509.14814","title":"ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance","created":"2025-09-18","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":"2605.01844","title":"The Cylindrical Representation Hypothesis for Language Model Steering","created":"2026-05-03","cited_by_count":5,"area":null},{"id":"2504.08016","title":"Emergence of psychopathological computations in large language models","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2506.16078","title":"Probing the Robustness of Large Language Models Safety to Latent Perturbations","created":"2025-06-19","cited_by_count":4,"area":"alignment"},{"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":"2410.02220","title":"Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks","created":"2024-10-03","cited_by_count":3,"area":"safety"},{"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":"2507.04404","title":"LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2510.01228","title":"Who is In Charge? Dissecting Role Conflicts in Instruction Following","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2602.07356","title":"Controllable Value Alignment in Large Language Models through Neuron-Level Editing","created":"2026-02-07","cited_by_count":3,"area":"alignment"},{"id":"2606.11599","title":"When is Your LLM Steerable?","created":"2026-06-10","cited_by_count":3,"area":"mechinterp"},{"id":"2607.25270","title":"Where Steering Signals Come From: Activation Source Selection in Activation Steering","created":"2026-07-28","cited_by_count":3,"area":"mechinterp"},{"id":"2608.05734","title":"Subliminal Learning is Non-Semantic Distillation","created":"2026-08-06","cited_by_count":3,"area":"mechinterp"},{"id":"2508.04530","title":"Balancing Stylization and Truth via Disentangled Representation Steering","created":"2025-08-06","cited_by_count":2,"area":"mechinterp"},{"id":"2603.17231","title":"Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2604.01202","title":"Therefore I am. I Think","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2605.05715","title":"Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2502.05945","title":"Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models","created":"2025-02-09","cited_by_count":1,"area":"safety"},{"id":"2503.14130","title":"Inference-Time Intervention in Large Language Models for Reliable Requirement Verification","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2510.02528","title":"Multimodal Function Vectors for Visual Relations","created":"2025-10-02","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":"2605.15687","title":"ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models","created":"2026-05-15","cited_by_count":1,"area":"mllm"},{"id":"2608.28806","title":"Enhancing SAE-based Steering via Neighbor Integrated Feature Selection","created":"2026-08-28","cited_by_count":1,"area":"mechinterp"},{"id":"2601.08169","title":"Relational Knowledge Distillation Using Fine-tuned Function Vectors","created":"2026-01-13","cited_by_count":0,"area":"distill"},{"id":"2603.06264","title":"Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2604.23877","title":"Knowledge Vector of Logical Reasoning in Large Language Models","created":"2026-04-26","cited_by_count":0,"area":"lr"},{"id":"2605.06196","title":"The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.24425","title":"Context Is King: How In-Context Specification Shapes the Geometry of Concepts","created":"2026-07-27","cited_by_count":0,"area":"wm"},{"id":"2608.16650","title":"PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.23124","title":"LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2610.06383","title":"Steering by Influence: Curvature Aware Data Weighting for Activation Steering","created":"2026-10-05","cited_by_count":0,"area":"mechinterp"},{"id":"2610.14025","title":"Contrastive Covariance Subspaces for Activation Steering","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2610.16325","title":"When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19359","title":"Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering","created":"2026-10-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}