{"total":64,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","cited_by_count":53,"area":"alignment"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"id":"2509.12886","title":"The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations","created":"2025-09-16","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":"2507.04742","title":"Activation Steering for Chain-of-Thought Compression","created":"2025-07-07","cited_by_count":24,"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":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2602.17560","title":"ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment","created":"2026-02-19","cited_by_count":19,"area":"alignment"},{"id":"2410.03804","title":"Mixture of Attentions For Speculative Decoding","created":"2024-10-04","cited_by_count":17,"area":"inference"},{"id":"2503.01048","title":"Personalize Your LLM: Fake it then Align it","created":"2025-03-02","cited_by_count":15,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2502.01208","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","created":"2025-02-03","cited_by_count":14,"area":"alignment"},{"id":"2411.08733","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models","created":"2024-11-13","cited_by_count":13,"area":"alignment"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2408.10668","title":"Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation","created":"2024-08-20","cited_by_count":10,"area":"safety"},{"id":"2509.21528","title":"Preemptive Detection and Steering of LLM Misalignment via Latent Reachability","created":"2025-09-25","cited_by_count":10,"area":"alignment"},{"id":"2510.01243","title":"Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing","created":"2025-09-24","cited_by_count":10,"area":"alignment"},{"id":"2412.07880","title":"Towards Foundation-model-based Multiagent System to Accelerate AI for Social Impact","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","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":"2505.20081","title":"Inference-time Alignment in Continuous Space","created":"2025-05-26","cited_by_count":7,"area":"alignment"},{"id":"2506.07434","title":"Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding","created":"2025-06-09","cited_by_count":7,"area":"alignment"},{"id":"2502.16944","title":"Pretrain Value, Not Reward: Decoupled Value Policy Optimization","created":"2025-02-24","cited_by_count":6,"area":"lr"},{"id":"2506.09085","title":"LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2503.10093","title":"Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling","created":"2025-03-13","cited_by_count":4,"area":"alignment"},{"id":"2602.20696","title":"PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding","created":"2026-02-24","cited_by_count":3,"area":null},{"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":"2606.08454","title":"Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior","created":"2026-06-07","cited_by_count":3,"area":"mechinterp"},{"id":"2606.10587","title":"Towards Diverse Scientific Hypothesis Search with Large Language Models","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2607.14943","title":"Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control","created":"2026-07-16","cited_by_count":3,"area":"wm"},{"id":"2502.20795","title":"Test-Time Alignment for Large Language Models via Textual Model Predictive Control","created":"2025-02-28","cited_by_count":2,"area":"alignment"},{"id":"2503.10617","title":"Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2504.06659","title":"Leveraging Machine Unlearning for Cost-Efficient Preference Alignment","created":"2025-04-09","cited_by_count":2,"area":"alignment"},{"id":"2508.04530","title":"Balancing Stylization and Truth via Disentangled Representation Steering","created":"2025-08-06","cited_by_count":2,"area":"mechinterp"},{"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":"2602.02572","title":"Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2602.21215","title":"Inference-time Alignment via Sparse Junction Steering","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2506.17828","title":"Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach","created":"2025-06-21","cited_by_count":1,"area":"alignment"},{"id":"2508.18212","title":"Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundaries","created":"2025-08-25","cited_by_count":1,"area":"alignment"},{"id":"2510.13727","title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","created":"2025-10-15","cited_by_count":1,"area":"safety"},{"id":"2510.24208","title":"Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2601.03464","title":"Prompting Underestimates LLM Capability for Time Series Classification","created":"2026-01-06","cited_by_count":1,"area":"mechinterp"},{"id":"2602.02060","title":"FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.18331","title":"Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equations","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2603.21461","title":"DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment","created":"2026-03-23","cited_by_count":1,"area":"alignment"},{"id":"2608.26120","title":"Recipes for Steering and Scaling LLMs via Sampling","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2505.00818","title":"Dual Filter: A Transformer-like Inference Architecture for Hidden Markov Models","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2508.13415","title":"MAVIS: Multi-Objective Alignment via Inference-Time Value-Guided Selection","created":"2025-08-19","cited_by_count":0,"area":"alignment"},{"id":"2510.09709","title":"The Idola Tribus of AI: Large Language Models tend to perceive order where none exists","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.26219","title":"Test-time reward-guided alignment of language models by importance sampling on pre-logit space","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2602.20102","title":"BarrierSteer: LLM Safety via Learning Barrier Steering","created":"2026-02-23","cited_by_count":0,"area":"safety"},{"id":"2604.23543","title":"Pref-CTRL: Preference Driven LLM Alignment using Representation Editing","created":"2026-04-26","cited_by_count":0,"area":"alignment"},{"id":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2608.08383","title":"Safety Cost of Steering Vectors Is Separable and Reducible","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2608.11692","title":"HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.14922","title":"SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable","created":"2026-08-14","cited_by_count":0,"area":"mechinterp"},{"id":"2608.30712","title":"GUIDE: Guiding Internal Evidence with Language Instructions","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.22243","title":"Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.30218","title":"Minimally Invasive Steering of Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33298","title":"Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2610.02844","title":"DNAlign: Dynamic Null-Space Safe Alignment for LLMs","created":"2026-10-02","cited_by_count":0,"area":"alignment"},{"id":"2610.04283","title":"First-Order Steering: Translating Weight Adaptation into Activation Steering","created":"2026-10-03","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}