{"total":29,"rows":[{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2508.07768","title":"Pareto Multi-Objective Alignment for Language Models","created":"2025-08-11","cited_by_count":20,"area":"alignment"},{"id":"2508.07172","title":"Gradient Surgery for Safe LLM Fine-Tuning","created":"2025-08-10","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":"2512.10150","title":"Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning","created":"2025-12-10","cited_by_count":10,"area":"alignment"},{"id":"2606.24993","title":"The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order","created":"2026-06-23","cited_by_count":9,"area":"alignment"},{"id":"2506.00569","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","created":"2025-05-31","cited_by_count":8,"area":"alignment"},{"id":"2406.00303","title":"Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning","created":"2024-06-01","cited_by_count":6,"area":"alignment"},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2503.23777","title":"CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment","created":"2025-03-31","cited_by_count":3,"area":"alignment"},{"id":"2603.17044","title":"Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models","created":"2026-03-17","cited_by_count":3,"area":"alignment"},{"id":"2606.07705","title":"SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models","created":"2026-06-05","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":"2512.00778","title":"What Is Preference Optimization Doing, and Why?","created":"2025-11-30","cited_by_count":2,"area":"alignment"},{"id":"2602.06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2604.05965","title":"Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment","created":"2026-04-07","cited_by_count":2,"area":"alignment"},{"id":"2503.03460","title":"Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models","created":"2025-03-05","cited_by_count":1,"area":"alignment"},{"id":"2512.06515","title":"ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","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":"2606.00357","title":"From \"Weak\" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2608.16553","title":"STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"id":"2601.04262","title":"Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis","created":"2026-01-07","cited_by_count":0,"area":"alignment"},{"id":"2604.20685","title":"MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment","created":"2026-04-22","cited_by_count":0,"area":"alignment"},{"id":"2605.28203","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2608.29492","title":"CoCoA: Context-Conditional Cultural Alignment for Large Language Models","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2609.34985","title":"ORPG: Reconciling Multiple Reward Objectives through Objective-wise Policy Gradients","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.20174","title":"RM-OPD: On-Policy Distillation for Generative Reward Models","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}