{"total":86,"rows":[{"id":"2510.07743","title":"OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment","created":"2025-10-09","cited_by_count":132,"area":"alignment"},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128,"area":"alignment"},{"id":"2509.23909","title":"EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling","created":"2025-09-28","cited_by_count":64,"area":"alignment"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2602.01511","title":"Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training","created":"2026-02-02","cited_by_count":54,"area":"alignment"},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2408.15549","title":"WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback","created":"2024-08-28","cited_by_count":31,"area":"alignment"},{"id":"2411.06208","title":"IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization","created":"2024-11-09","cited_by_count":31,"area":"alignment"},{"id":"2511.23002","title":"JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization","created":"2025-11-28","cited_by_count":31,"area":"alignment"},{"id":"2503.17239","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","created":"2025-03-21","cited_by_count":25,"area":"alignment"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2410.18640","title":"Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model","created":"2024-10-24","cited_by_count":22,"area":"alignment"},{"id":"2405.12739","title":"SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling","created":"2024-05-21","cited_by_count":21,"area":"alignment"},{"id":"2412.11041","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","created":"2024-12-15","cited_by_count":20,"area":"alignment"},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","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":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"area":"alignment"},{"id":"2501.18457","title":"CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering","created":"2025-01-30","cited_by_count":10,"area":"alignment"},{"id":"2505.11166","title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","created":"2025-05-16","cited_by_count":10,"area":"alignment"},{"id":"2604.02795","title":"Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks","created":"2026-04-03","cited_by_count":10,"area":"alignment"},{"id":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2505.16610","title":"From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment","created":"2025-05-22","cited_by_count":9,"area":"alignment"},{"id":"2505.17072","title":"Safety Alignment Can Be Not Superficial With Explicit Safety Signals","created":"2025-05-19","cited_by_count":9,"area":"alignment"},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2602.16660","title":"Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment","created":"2026-02-18","cited_by_count":9,"area":"alignment"},{"id":"2603.08091","title":"Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization","created":"2026-03-09","cited_by_count":9,"area":"alignment"},{"id":"2603.12247","title":"Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation","created":"2026-03-12","cited_by_count":9,"area":"alignment"},{"id":"2502.05478","title":"OntoTune: Ontology-Driven Self-training for Aligning Large Language Models","created":"2025-02-08","cited_by_count":8,"area":"alignment"},{"id":"2502.16645","title":"CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale","created":"2025-02-23","cited_by_count":8,"area":"alignment"},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"id":"2512.23457","title":"Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following","created":"2025-12-29","cited_by_count":8,"area":"alignment"},{"id":"2412.03253","title":"Alignment at Pre-training! Towards Native Alignment for Arabic LLMs","created":"2024-12-04","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":"2506.18245","title":"Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection","created":"2025-06-23","cited_by_count":7,"area":"alignment"},{"id":"2512.04784","title":"PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling","created":"2025-12-02","cited_by_count":7,"area":"alignment"},{"id":"2409.13948","title":"Aligning Language Models Using Follow-up Likelihood as Reward Signal","created":"2024-09-20","cited_by_count":6,"area":"alignment"},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2504.15843","title":"Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model","created":"2025-04-22","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":"2603.03192","title":"MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization","created":"2026-03-03","cited_by_count":6,"area":"alignment"},{"id":"2407.01470","title":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","created":"2024-07-01","cited_by_count":5,"area":"alignment"},{"id":"2408.09834","title":"Minor DPO reject penalty to increase training robustness","created":"2024-08-19","cited_by_count":5,"area":"alignment"},{"id":"2410.17131","title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","created":"2024-10-22","cited_by_count":5,"area":"alignment"},{"id":"2505.16995","title":"DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization","created":"2025-05-22","cited_by_count":5,"area":"alignment"},{"id":"2605.29156","title":"RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains","created":"2026-05-27","cited_by_count":5,"area":"alignment"},{"id":"2511.06778","title":"SAFENLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces","created":"2025-11-10","cited_by_count":4,"area":"alignment"},{"id":"2511.11518","title":"W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search","created":"2025-11-14","cited_by_count":4,"area":"alignment"},{"id":"2408.10642","title":"Minor SFT loss for LLM fine-tune to increase performance and reduce model deviation","created":"2024-08-20","cited_by_count":3,"area":"alignment"},{"id":"2408.12579","title":"RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment","created":"2024-08-22","cited_by_count":3,"area":"alignment"},{"id":"2503.04249","title":"How to Mitigate Overfitting in Weak-to-strong Generalization?","created":"2025-03-06","cited_by_count":3,"area":"alignment"},{"id":"2505.22172","title":"Reverse Preference Optimization for Complex Instruction Following","created":"2025-05-28","cited_by_count":3,"area":"alignment"},{"id":"2508.17637","title":"Weights-Rotated Preference Optimization for Large Language Models","created":"2025-08-25","cited_by_count":3,"area":"alignment"},{"id":"2510.18849","title":"Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning","created":"2025-10-21","cited_by_count":3,"area":"alignment"},{"id":"2511.00040","title":"Semi-Supervised Preference Optimization with Limited Feedback","created":"2025-10-28","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":"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":"2505.23114","title":"Alignment Data Map for Efficient Preference Data Selection and Diagnosis","created":"2025-05-29","cited_by_count":2,"area":"alignment"},{"id":"2605.01507","title":"MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2608.21839","title":"FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling","created":"2026-08-22","cited_by_count":2,"area":"alignment"},{"id":"2410.15651","title":"Understanding and Alleviating Memory Consumption in RLHF for LLMs","created":"2024-10-21","cited_by_count":1,"area":"alignment"},{"id":"2502.03843","title":"Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis","created":"2025-02-06","cited_by_count":1,"area":"alignment"},{"id":"2505.19743","title":"Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2506.21497","title":"Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments","created":"2025-06-26","cited_by_count":1,"area":"alignment"},{"id":"2603.02225","title":"Scaling Reward Modeling without Human Supervision","created":"2026-02-11","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":"2608.24231","title":"RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges","created":"2026-08-25","cited_by_count":1,"area":"alignment"},{"id":"2503.04346","title":"Adding Alignment Control to Language Models","created":"2025-03-06","cited_by_count":0,"area":"alignment"},{"id":"2506.09096","title":"Intra-Trajectory Consistency for Reward Modeling","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2507.03673","title":"TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection","created":"2025-07-04","cited_by_count":0,"area":"alignment"},{"id":"2508.01302","title":"Aligning Language Models with Real-time Knowledge Editing","created":"2025-08-02","cited_by_count":0,"area":"alignment"},{"id":"2509.05605","title":"Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation","created":"2025-09-06","cited_by_count":0,"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":"2511.09880","title":"EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models","created":"2025-11-13","cited_by_count":0,"area":"alignment"},{"id":"2602.02063","title":"See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2605.04572","title":"From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning","created":"2026-05-06","cited_by_count":0,"area":"alignment"},{"id":"2605.28597","title":"Position: Retire the \"Positive Backdoor\" Label -- Secret Alignment Requires Strict and Systematic Evaluation","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2605.31126","title":"Not All Synthetic Data Is Yours to Learn From","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2607.07993","title":"Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"id":"2608.26779","title":"Instruction Quality Matters: Refining Instructions for Effective Preference Learning","created":"2026-08-27","cited_by_count":0,"area":"alignment"},{"id":"2609.00921","title":"VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.02273","title":"CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging","created":"2026-09-02","cited_by_count":0,"area":"alignment"},{"id":"2609.32189","title":"ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2610.19365","title":"DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}