{"total":34,"rows":[{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2505.23556","title":"Understanding Refusal in Language Models with Sparse Autoencoders","created":"2025-05-29","cited_by_count":29,"area":"alignment"},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2508.08746","title":"Interpretable Reward Model via Sparse Autoencoder","created":"2025-08-12","cited_by_count":18,"area":"alignment"},{"id":"2409.02231","title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","created":"2024-09-03","cited_by_count":14,"area":"alignment"},{"id":"2411.07618","title":"Constrain Alignment with Sparse Autoencoders","created":"2024-11-12","cited_by_count":12,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2602.11180","title":"Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions","created":"2026-01-21","cited_by_count":8,"area":"alignment"},{"id":"2509.07961","title":"Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare","created":"2025-09-09","cited_by_count":7,"area":"alignment"},{"id":"2507.00665","title":"SAFER: Probing Safety in Reward Models with Sparse Autoencoder","created":"2025-07-01","cited_by_count":6,"area":"alignment"},{"id":"2411.06424","title":"How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis","created":"2024-11-10","cited_by_count":5,"area":"alignment"},{"id":"2509.12934","title":"The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features","created":"2025-09-16","cited_by_count":5,"area":"alignment"},{"id":"2512.23260","title":"Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"id":"2310.08164","title":"Interpreting Learned Feedback Patterns in Large Language Models","created":"2023-10-12","cited_by_count":4,"area":"alignment"},{"id":"2509.23982","title":"Toward Preference-aligned Large Language Models via Residual-based Model Steering","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2510.13154","title":"The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs","created":"2025-10-15","cited_by_count":3,"area":"alignment"},{"id":"2509.19839","title":"LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation","created":"2025-09-24","cited_by_count":2,"area":"alignment"},{"id":"2605.23035","title":"Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography","created":"2026-05-21","cited_by_count":2,"area":"alignment"},{"id":"2606.09850","title":"Mechanistic Analysis of Alignment Algorithms in Language Models","created":"2026-05-09","cited_by_count":2,"area":"alignment"},{"id":"2504.07965","title":"Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments","created":"2025-04-10","cited_by_count":1,"area":"alignment"},{"id":"2510.16257","title":"Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2603.21461","title":"DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment","created":"2026-03-23","cited_by_count":1,"area":"alignment"},{"id":"2604.27401","title":"Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs","created":"2026-04-30","cited_by_count":1,"area":"alignment"},{"id":"2605.16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2606.08496","title":"SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization","created":"2026-06-07","cited_by_count":1,"area":"alignment"},{"id":"2505.15626","title":"Direct Preference Optimization for Adaptive Concept-based Explanations","created":"2025-05-21","cited_by_count":0,"area":"alignment"},{"id":"2602.02304","title":"Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2603.06727","title":"Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2605.28722","title":"Multi-Adapter Representation Interventions via Energy Calibration","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2608.02674","title":"Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"id":"2608.05409","title":"Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment","created":"2026-08-05","cited_by_count":0,"area":"alignment"},{"id":"2608.29936","title":"When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2609.06289","title":"Steering Geometry: Validating Human Value Geometry in LLM Steering Space","created":"2026-09-05","cited_by_count":0,"area":"alignment"}],"next_cursor":null}