{"total":47,"rows":[{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"area":"alignment"},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2505.20259","title":"Lifelong Safety Alignment for Language Models","created":"2025-05-26","cited_by_count":15,"area":"alignment"},{"id":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.14681","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","created":"2025-06-17","cited_by_count":14,"area":"alignment"},{"id":"2505.21605","title":"SoSBench: Benchmarking Safety Alignment on Six Scientific Domains","created":"2025-05-27","cited_by_count":12,"area":"alignment"},{"id":"2506.00419","title":"Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2505.00038","title":"HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation","created":"2025-04-29","cited_by_count":7,"area":"alignment"},{"id":"2603.11388","title":"Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment","created":"2026-03-12","cited_by_count":7,"area":"alignment"},{"id":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","cited_by_count":6,"area":"alignment"},{"id":"2602.07892","title":"Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection","created":"2026-02-08","cited_by_count":6,"area":"alignment"},{"id":"2602.14777","title":"Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment","created":"2026-02-16","cited_by_count":6,"area":"alignment"},{"id":"2502.03397","title":"SPRI: Aligning Large Language Models with Context-Situated Principles","created":"2025-02-05","cited_by_count":5,"area":"alignment"},{"id":"2502.05934","title":"Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity Analysis","created":"2025-02-09","cited_by_count":5,"area":"alignment"},{"id":"2506.04679","title":"Normative Conflicts and Shallow AI Alignment","created":"2025-06-05","cited_by_count":5,"area":"alignment"},{"id":"2507.15328","title":"On the Inevitability of Left-Leaning Political Bias in Aligned Language Models","created":"2025-07-21","cited_by_count":4,"area":"alignment"},{"id":"2606.24014","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models","created":"2026-06-22","cited_by_count":4,"area":"alignment"},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2601.19231","title":"LLMs Can Unlearn Refusal with Only 1,000 Benign Samples","created":"2026-01-27","cited_by_count":3,"area":"alignment"},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"area":"alignment"},{"id":"2502.11853","title":"StructTransform: A Scalable Attack Surface for Safety-Aligned Large Language Models","created":"2025-02-17","cited_by_count":2,"area":"alignment"},{"id":"2503.04740","title":"PRISM: Perspective Reasoning for Integrated Synthesis and Mediation as a Multi-Perspective Framework for AI Alignment","created":"2025-02-05","cited_by_count":2,"area":"alignment"},{"id":"2509.01938","title":"EigenBench: A Comparative Behavioral Measure of Value Alignment","created":"2025-09-02","cited_by_count":2,"area":"alignment"},{"id":"2511.06512","title":"EASE: Practical and Efficient Safety Alignment for Small Language Models","created":"2025-11-09","cited_by_count":2,"area":"alignment"},{"id":"2602.12180","title":"How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics","created":"2026-02-12","cited_by_count":2,"area":"alignment"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2606.16276","title":"SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data","created":"2026-06-15","cited_by_count":2,"area":"alignment"},{"id":"2605.29396","title":"Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2510.09004","title":"Decoupling Safety into Orthogonal Subspace: Cost-Efficient and Performance-Preserving Alignment for Large Language Models","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2602.00619","title":"Jailbreaking LLMs via Calibration","created":"2026-01-31","cited_by_count":0,"area":"alignment"},{"id":"2604.17210","title":"Guardrails in Logit Space: Safety Token Regularization for LLM Alignment","created":"2026-04-19","cited_by_count":0,"area":"alignment"},{"id":"2606.15517","title":"SHARD: Safe and Helpful Alignment via Self-Reframing Distillation","created":"2026-06-14","cited_by_count":0,"area":"alignment"},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2607.02914","title":"Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2607.17946","title":"A Geometric Perspective on Stabilizing Value Conflict Resolution","created":"2026-07-20","cited_by_count":0,"area":"alignment"},{"id":"2608.09551","title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.29378","title":"Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration","created":"2026-08-29","cited_by_count":0,"area":"alignment"},{"id":"2609.19325","title":"AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment","created":"2026-09-16","cited_by_count":0,"area":"alignment"},{"id":"2609.38645","title":"Alignment via Training Against Probes Without Losing Monitorability","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.07935","title":"SIGMA: Self-Improving Alignment Generalization from a Model Spec","created":"2026-10-06","cited_by_count":0,"area":"alignment"},{"id":"2610.12233","title":"ReSI: Recursive Safety Improvement toward Resistant and Resilient AI","created":"2026-10-08","cited_by_count":0,"area":"alignment"}],"next_cursor":null}