{"total":77,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2506.09937","title":"SAFE: Multitask Failure Detection for Vision-Language-Action Models","created":"2025-06-11","cited_by_count":80,"area":"vla"},{"id":"2505.22101","title":"MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models","created":"2025-05-28","cited_by_count":73,"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":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50,"area":"alignment"},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2504.09466","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","created":"2025-04-13","cited_by_count":38,"area":"alignment"},{"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":"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":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2505.18325","title":"Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary","created":"2025-05-23","cited_by_count":18,"area":"safety"},{"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":"2505.12584","title":"Improving Multilingual Language Models by Aligning Representations through Steering","created":"2025-05-19","cited_by_count":11,"area":null},{"id":"2507.08799","title":"KV Cache Steering for Controlling Frozen LLMs","created":"2025-07-11","cited_by_count":11,"area":"inference"},{"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":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"id":"2510.04217","title":"MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering","created":"2025-10-05","cited_by_count":10,"area":"mllm"},{"id":"2505.13636","title":"Incentivizing Truthful Language Models via Peer Elicitation Games","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2506.08572","title":"The Geometries of Truth Are Orthogonal Across Tasks","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2505.20309","title":"Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs","created":"2025-05-22","cited_by_count":8,"area":"mechinterp"},{"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":"2508.17621","title":"Steering When Necessary: Flexible Steering Large Language Models with Backtracking","created":"2025-08-25","cited_by_count":8,"area":"mechinterp"},{"id":"2510.26769","title":"SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models","created":"2025-10-30","cited_by_count":8,"area":"mllm"},{"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":"2603.01281","title":"Spectral Attention Steering for Prompt Highlighting","created":"2026-03-01","cited_by_count":8,"area":null},{"id":"2503.02989","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","created":"2025-03-04","cited_by_count":7,"area":"alignment"},{"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":"2510.05498","title":"Prototype-Based Dynamic Steering for Large Language Models","created":"2025-10-07","cited_by_count":6,"area":"lr"},{"id":"2603.02237","title":"Concept Heterogeneity-aware Representation Steering","created":"2026-02-13","cited_by_count":6,"area":"mechinterp"},{"id":"2603.06745","title":"Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection","created":"2026-03-06","cited_by_count":6,"area":"mechinterp"},{"id":"2501.19398","title":"Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game","created":"2025-01-31","cited_by_count":5,"area":"agents"},{"id":"2508.08730","title":"Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation","created":"2025-08-12","cited_by_count":5,"area":null},{"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":"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":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"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":"2507.15676","title":"Agentic AI for autonomous anomaly management in complex systems","created":"2025-07-21","cited_by_count":4,"area":"agents"},{"id":"2602.08159","title":"The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models","created":"2026-02-08","cited_by_count":4,"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":"2605.17028","title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.01479","title":"Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech","created":"2026-05-31","cited_by_count":3,"area":"mechinterp"},{"id":"2606.08454","title":"Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior","created":"2026-06-07","cited_by_count":3,"area":"mechinterp"},{"id":"2608.08829","title":"Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models","created":"2026-08-09","cited_by_count":3,"area":"mechinterp"},{"id":"2505.24232","title":"From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2510.07775","title":"The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs","created":"2025-10-09","cited_by_count":2,"area":"safety"},{"id":"2512.19456","title":"Activations as Features: Probing LLMs for Generalizable Essay Scoring Representations","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2603.27518","title":"Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs","created":"2026-03-29","cited_by_count":2,"area":"alignment"},{"id":"2604.04743","title":"Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2502.03618","title":"The Logical Implication Steering Method for Conditional Interventions on Transformer Generation","created":"2025-02-05","cited_by_count":1,"area":"mechinterp"},{"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":"2506.18887","title":"Steering Conceptual Bias via Transformer Latent-Subspace Activation","created":"2025-06-23","cited_by_count":1,"area":"mechinterp"},{"id":"2510.17590","title":"MERIT: Modular Framework for Multimodal Misinformation Detection with Web-Grounded Reasoning","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2511.14195","title":"N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator","created":"2025-11-18","cited_by_count":1,"area":"safety"},{"id":"2601.23157","title":"No More, No Less: Least-Privilege Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2609.00823","title":"Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.01878","title":"GAPS: Dimension-Level Gates for Conditional Activation Steering","created":"2026-09-01","cited_by_count":1,"area":"mechinterp"},{"id":"2609.18998","title":"One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2410.12927","title":"Deep Model Merging: The Sister of Neural Network Interpretability -- A Survey","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2508.06963","title":"MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair","created":"2025-08-09","cited_by_count":0,"area":"agents"},{"id":"2510.12672","title":"Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers","created":"2025-10-14","cited_by_count":0,"area":"safety"},{"id":"2602.01897","title":"Internal Flow Signatures for Self-Checking and Refinement in LLMs","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.18163","title":"TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.04155","title":"SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.09635","title":"Gradient-Guided Reward Optimization for Inference-time Alignment","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2607.18259","title":"Probabilistic Concept-Aware Steering for Trustworthy LLM Inference","created":"2026-05-15","cited_by_count":0,"area":"mechinterp"},{"id":"2608.29215","title":"Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation","created":"2026-08-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.00608","title":"Investigating Assistant Bias in LLM User Simulators Using a Role Vector","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.06289","title":"Steering Geometry: Validating Human Value Geometry in LLM Steering Space","created":"2026-09-05","cited_by_count":0,"area":"alignment"},{"id":"2609.30405","title":"Adaptive Multi-Value Control in LLMs via Causal Activation Steering","created":"2026-09-24","cited_by_count":0,"area":"mechinterp"},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04183","title":"Language Model Activations Inhabit Privileged Error-Correcting Basins","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04245","title":"On the Steering Dimensionality of Refusal in Language Models","created":"2026-10-03","cited_by_count":0,"area":"safety"},{"id":"2610.04967","title":"One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering","created":"2026-10-04","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}