{"total":83,"rows":[{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"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":"2503.15477","title":"What Makes a Reward Model a Good Teacher? An Optimization Perspective","created":"2025-03-19","cited_by_count":73,"area":"alignment"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"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":"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":"2603.01562","title":"RubricBench: Aligning Model-Generated Rubrics with Human Standards","created":"2026-03-02","cited_by_count":28,"area":"alignment"},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2511.01689","title":"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI","created":"2025-11-03","cited_by_count":24,"area":"alignment"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","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":"2512.16899","title":"Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image","created":"2025-12-18","cited_by_count":20,"area":"alignment"},{"id":"2511.16955","title":"Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models","created":"2025-11-21","cited_by_count":16,"area":"alignment"},{"id":"2605.03871","title":"EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics","created":"2026-05-05","cited_by_count":13,"area":"alignment"},{"id":"2506.21463","title":"Aligning Spoken Dialogue Models from User Interactions","created":"2025-06-26","cited_by_count":11,"area":"alignment"},{"id":"2601.07349","title":"Reward Modeling from Natural Language Human Feedback","created":"2026-01-12","cited_by_count":11,"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":"2507.21983","title":"Improving Generative Ad Text on Facebook using Reinforcement Learning","created":"2025-07-29","cited_by_count":9,"area":"alignment"},{"id":"2608.11669","title":"Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL","created":"2026-08-12","cited_by_count":9,"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":"2508.04149","title":"Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap","created":"2025-08-06","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":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"id":"2602.03876","title":"GOPO: Policy Optimization using Ranked Rewards","created":"2026-02-01","cited_by_count":5,"area":"alignment"},{"id":"2502.11284","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","created":"2025-02-16","cited_by_count":4,"area":"alignment"},{"id":"2502.13603","title":"Efficient Safety Retrofitting Against Jailbreaking for LLMs","created":"2025-02-19","cited_by_count":4,"area":"alignment"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2601.03589","title":"OLA: Output Language Alignment in Code-Switched LLM Interactions","created":"2026-01-07","cited_by_count":3,"area":"alignment"},{"id":"2602.24040","title":"RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models","created":"2026-02-27","cited_by_count":3,"area":"alignment"},{"id":"2603.05739","title":"Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment","created":"2026-03-05","cited_by_count":3,"area":"alignment"},{"id":"2604.13618","title":"C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences","created":"2026-04-15","cited_by_count":3,"area":"alignment"},{"id":"2606.21795","title":"Discretizing Reward Models","created":"2026-06-19","cited_by_count":3,"area":"alignment"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2509.21798","title":"Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment","created":"2025-09-26","cited_by_count":2,"area":"alignment"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2510.06096","title":"The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives","created":"2025-10-07","cited_by_count":2,"area":"alignment"},{"id":"2603.09692","title":"ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2607.01083","title":"Staleness-Learning Rate Scaling Laws for Asynchronous RLHF","created":"2026-07-01","cited_by_count":2,"area":"alignment"},{"id":"2608.31079","title":"Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization","created":"2026-08-31","cited_by_count":2,"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":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2510.20187","title":"Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values","created":"2025-10-23","cited_by_count":1,"area":"alignment"},{"id":"2602.16802","title":"References Improve LLM Alignment in Non-Verifiable Domains","created":"2026-02-18","cited_by_count":1,"area":"alignment"},{"id":"2604.25872","title":"When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient","created":"2026-04-28","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":"2606.19168","title":"Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2609.25760","title":"The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance","created":"2026-09-22","cited_by_count":1,"area":"alignment"},{"id":"2502.04567","title":"Preference Optimization via Contrastive Divergence: Your Reward Model is Secretly an NLL Estimator","created":"2025-02-06","cited_by_count":0,"area":"alignment"},{"id":"2511.06682","title":"Textual Self-attention Network: Test-Time Preference Optimization through Textual Gradient-based Attention","created":"2025-11-10","cited_by_count":0,"area":"alignment"},{"id":"2604.07754","title":"The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training","created":"2026-04-09","cited_by_count":0,"area":"alignment"},{"id":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.01060","title":"MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","created":"2026-06-08","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":"2607.03453","title":"Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2607.16195","title":"Rater State Bias in RLHF Preference Data: An Audit Framework","created":"2026-04-14","cited_by_count":0,"area":"alignment"},{"id":"2608.06179","title":"SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models","created":"2026-08-06","cited_by_count":0,"area":"alignment"},{"id":"2608.13854","title":"Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision","created":"2026-08-14","cited_by_count":0,"area":"alignment"},{"id":"2608.15402","title":"Towards a theory of inference-time alignment with unknown rewards","created":"2026-08-15","cited_by_count":0,"area":"alignment"},{"id":"2608.16926","title":"Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training","created":"2026-08-05","cited_by_count":0,"area":"alignment"},{"id":"2608.19748","title":"Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.29352","title":"Cross-Relational Preference Learning for Better LLM Instruction Following","created":"2026-08-29","cited_by_count":0,"area":"alignment"},{"id":"2609.02170","title":"DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation","created":"2026-09-02","cited_by_count":0,"area":"alignment"},{"id":"2609.06934","title":"The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.23665","title":"Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation","created":"2026-09-20","cited_by_count":0,"area":"alignment"},{"id":"2609.29421","title":"Rufus-Air: An Open LLM Post-Training Recipe","created":"2026-09-24","cited_by_count":0,"area":"alignment"},{"id":"2609.30226","title":"PoEM: Predicting RL Outcomes from Existing Policies","created":"2026-09-24","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":"2609.33086","title":"From Constitutions to Control: Interpretable Rewards for Aligning Language Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.33803","title":"Diffusion Reward Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.35677","title":"Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.01821","title":"Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.03458","title":"A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control","created":"2026-10-02","cited_by_count":0,"area":"alignment"},{"id":"2610.06360","title":"Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering","created":"2026-10-05","cited_by_count":0,"area":"alignment"},{"id":"2610.06670","title":"Reward Stealing Attack on Large Language Models","created":"2026-10-05","cited_by_count":0,"area":"alignment"},{"id":"2610.12822","title":"Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems","created":"2026-10-09","cited_by_count":0,"area":"alignment"},{"id":"2610.19525","title":"Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following","created":"2026-10-14","cited_by_count":0,"area":"alignment"},{"id":"2610.19832","title":"Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}