{"total":124,"rows":[{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196,"area":"alignment"},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2406.05534","title":"Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing","created":"2024-06-08","cited_by_count":39,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2403.05006","title":"Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback","created":"2024-03-08","cited_by_count":32,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2505.06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model","created":"2025-05-06","cited_by_count":28,"area":"alignment"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2502.14860","title":"ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning","created":"2025-02-20","cited_by_count":25,"area":"lr"},{"id":"2508.03905","title":"Sotopia-RL: Reward Design for Social Intelligence","created":"2025-08-05","cited_by_count":24,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2503.00295","title":"Robust Multi-Objective Preference Alignment with Online DPO","created":"2025-03-01","cited_by_count":22,"area":"alignment"},{"id":"2406.07529","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2412.05469","title":"Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization","created":"2024-12-06","cited_by_count":20,"area":"alignment"},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2501.10945","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","created":"2025-01-19","cited_by_count":18,"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":"2502.14354","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","created":"2025-02-20","cited_by_count":16,"area":"lr"},{"id":"2507.13541","title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","created":"2025-07-17","cited_by_count":16,"area":null},{"id":"2407.17466","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","created":"2024-07-24","cited_by_count":15,"area":"deeprl"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13,"area":"alignment"},{"id":"2505.24445","title":"Learning Safety Constraints for Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"safety"},{"id":"2507.04756","title":"CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2502.18635","title":"Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems","created":"2025-02-25","cited_by_count":12,"area":"rag"},{"id":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2605.27141","title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","created":"2026-05-26","cited_by_count":12,"area":"agents"},{"id":"2410.24175","title":"Constraint Back-translation Improves Complex Instruction Following of Large Language Models","created":"2024-10-31","cited_by_count":11,"area":null},{"id":"2502.15145","title":"Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF","created":"2025-02-21","cited_by_count":11,"area":"alignment"},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2512.11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","created":"2025-12-12","cited_by_count":11,"area":"alignment"},{"id":"2602.02495","title":"Reward-free Alignment for Conflicting Objectives","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2502.18699","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","created":"2025-02-25","cited_by_count":10,"area":"alignment"},{"id":"2504.10823","title":"CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2505.19770","title":"Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO","created":"2025-05-26","cited_by_count":10,"area":"alignment"},{"id":"2603.26680","title":"AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment","created":"2026-03-09","cited_by_count":10,"area":null},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2405.12961","title":"Aligning Transformers with Continuous Feedback via Energy Rank Alignment","created":"2024-05-21","cited_by_count":7,"area":"alignment"},{"id":"2412.20984","title":"Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2502.20757","title":"The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents","created":"2025-02-28","cited_by_count":7,"area":"agents"},{"id":"2504.04215","title":"Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability","created":"2025-04-05","cited_by_count":7,"area":"mechinterp"},{"id":"2505.04993","title":"Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes","created":"2025-05-08","cited_by_count":7,"area":"alignment"},{"id":"2509.24610","title":"OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"id":"2503.12575","title":"BalancedDPO: Adaptive Multi-Metric Alignment","created":"2025-03-16","cited_by_count":6,"area":"diffusion"},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2506.07165","title":"AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models","created":"2025-06-08","cited_by_count":6,"area":"alignment"},{"id":"2510.01167","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","created":"2025-10-01","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":"2410.08316","title":"COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework","created":"2024-10-10","cited_by_count":5,"area":"alignment"},{"id":"2410.19471","title":"Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2504.11337","title":"REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective","created":"2025-04-15","cited_by_count":5,"area":"alignment"},{"id":"2602.07164","title":"Your Language Model Secretly Contains Personality Subnetworks","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2502.04357","title":"Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs","created":"2025-02-04","cited_by_count":4,"area":"lr"},{"id":"2504.16628","title":"ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data","created":"2025-04-23","cited_by_count":4,"area":"alignment"},{"id":"2602.17695","title":"EXACT: Explicit Attribute-Guided Decoding-Time Personalization","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2605.26579","title":"Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards","created":"2026-05-26","cited_by_count":4,"area":"deeprl"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2410.21533","title":"L3Ms -- Lagrange Large Language Models","created":"2024-10-28","cited_by_count":3,"area":"alignment"},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2508.11255","title":"FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation","created":"2025-08-15","cited_by_count":3,"area":"alignment"},{"id":"2509.23371","title":"Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization","created":"2025-09-27","cited_by_count":3,"area":"alignment"},{"id":"2512.23067","title":"The Reward Model Selection Crisis in Personalized Alignment","created":"2025-12-28","cited_by_count":3,"area":"alignment"},{"id":"2602.09538","title":"UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"id":"2606.16771","title":"GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization","created":"2026-06-15","cited_by_count":3,"area":"alignment"},{"id":"2608.03092","title":"SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation","created":"2026-08-04","cited_by_count":3,"area":"alignment"},{"id":"2503.10669","title":"UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality","created":"2025-03-10","cited_by_count":2,"area":"alignment"},{"id":"2503.12301","title":"One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2505.11983","title":"Online Iterative Self-Alignment for Radiology Report Generation","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2505.20336","title":"MOSLIM:Align with diverse preferences in prompts through reward classification","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","cited_by_count":2,"area":null},{"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":"2608.16072","title":"Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization","created":"2026-08-17","cited_by_count":2,"area":"deeprl"},{"id":"2503.01233","title":"PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation","created":"2025-03-03","cited_by_count":1,"area":"alignment"},{"id":"2506.00805","title":"HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models","created":"2025-06-01","cited_by_count":1,"area":"mllm"},{"id":"2506.06715","title":"A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2507.00026","title":"RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2508.07638","title":"Data Selection for LLM Alignment Using Fine-Grained Preferences","created":"2025-08-11","cited_by_count":1,"area":"alignment"},{"id":"2508.10530","title":"Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?","created":"2025-08-14","cited_by_count":1,"area":"alignment"},{"id":"2510.15716","title":"Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2511.01891","title":"Multi-Personality Generation of LLMs at Decoding-time","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.06515","title":"ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"id":"2512.24555","title":"From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme","created":"2025-12-31","cited_by_count":1,"area":"lr"},{"id":"2601.04300","title":"Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes","created":"2026-01-07","cited_by_count":1,"area":"diffusion"},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.00979","title":"Dual Optimal: Make Your LLM Peer-like with Dignity","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2604.04497","title":"One Model for All: Multi-Objective Controllable Language Models","created":"2026-04-06","cited_by_count":1,"area":"alignment"},{"id":"2604.17299","title":"Cat-DPO: Category-Adaptive Safety Alignment","created":"2026-04-19","cited_by_count":1,"area":"alignment"},{"id":"2605.11679","title":"Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion","created":"2026-05-12","cited_by_count":1,"area":"alignment"},{"id":"2605.18721","title":"General Preference Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"alignment"},{"id":"2605.19330","title":"MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2605.24154","title":"Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs","created":"2026-05-22","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}