{"total":157,"rows":[{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142,"area":"alignment"},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2407.13399","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","created":"2024-07-18","cited_by_count":78,"area":"alignment"},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"area":"alignment"},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"area":"alignment"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"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":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2405.20850","title":"Improving Reward Models with Synthetic Critiques","created":"2024-05-31","cited_by_count":44,"area":"alignment"},{"id":"2311.00168","title":"The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback","created":"2023-10-31","cited_by_count":42,"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":"2402.13210","title":"Bayesian Reward Models for LLM Alignment","created":"2024-02-20","cited_by_count":35,"area":"alignment"},{"id":"2412.19792","title":"InfAlign: Inference-aware language model alignment","created":"2024-12-27","cited_by_count":35,"area":"alignment"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33,"area":"alignment"},{"id":"2410.18013","title":"Scalable Ranked Preference Optimization for Text-to-Image Generation","created":"2024-10-23","cited_by_count":33,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2402.04229","title":"MusicRL: Aligning Music Generation to Human Preferences","created":"2024-02-06","cited_by_count":32,"area":"alignment"},{"id":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"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":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"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":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2409.03650","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","created":"2024-09-05","cited_by_count":27,"area":"alignment"},{"id":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26,"area":"alignment"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2503.22230","title":"Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback","created":"2025-03-28","cited_by_count":26,"area":"alignment"},{"id":"2402.00742","title":"Transforming and Combining Rewards for Aligning Large Language Models","created":"2024-02-01","cited_by_count":25,"area":"alignment"},{"id":"2404.01054","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2406.15568","title":"Robust Reinforcement Learning from Corrupted Human Feedback","created":"2024-06-21","cited_by_count":25,"area":"alignment"},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2506.14175","title":"GRAM: A Generative Foundation Reward Model for Reward Generalization","created":"2025-06-17","cited_by_count":25,"area":"alignment"},{"id":"2404.13846","title":"Filtered Direct Preference Optimization","created":"2024-04-22","cited_by_count":24,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2403.07708","title":"Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards","created":"2024-03-12","cited_by_count":23,"area":"alignment"},{"id":"2406.05883","title":"Information Theoretic Guarantees For Policy Alignment In Large Language Models","created":"2024-06-09","cited_by_count":23,"area":"alignment"},{"id":"2409.06957","title":"Policy Filtration for RLHF to Mitigate Noise in Reward Models","created":"2024-09-11","cited_by_count":22,"area":"alignment"},{"id":"2409.08813","title":"Your Weak LLM is Secretly a Strong Teacher for Alignment","created":"2024-09-13","cited_by_count":20,"area":"alignment"},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18,"area":"alignment"},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2403.01197","title":"DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling","created":"2024-03-02","cited_by_count":15,"area":"alignment"},{"id":"2403.19279","title":"Fine-Tuning Language Models with Reward Learning on Policy","created":"2024-03-28","cited_by_count":15,"area":"alignment"},{"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":"2503.18130","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization","created":"2025-03-23","cited_by_count":14,"area":"alignment"},{"id":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13,"area":"alignment"},{"id":"2407.03038","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","created":"2024-07-03","cited_by_count":13,"area":"alignment"},{"id":"2505.07271","title":"On the Robustness of Reward Models for Language Model Alignment","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"id":"2505.10527","title":"WorldPM: Scaling Human Preference Modeling","created":"2025-05-15","cited_by_count":13,"area":"alignment"},{"id":"2506.05339","title":"Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models","created":"2025-06-05","cited_by_count":13,"area":"alignment"},{"id":"2601.22664","title":"Real-Time Aligned Reward Model beyond Semantics","created":"2026-01-30","cited_by_count":13,"area":"alignment"},{"id":"2503.00539","title":"Distributionally Robust Reinforcement Learning with Human Feedback","created":"2025-03-01","cited_by_count":12,"area":"alignment"},{"id":"2505.18126","title":"Reward Model Overoptimisation in Iterated RLHF","created":"2025-05-23","cited_by_count":12,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2505.12763","title":"Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization","created":"2025-05-19","cited_by_count":11,"area":"alignment"},{"id":"2505.13487","title":"Detecting Prefix Bias in LLM-based Reward Models","created":"2025-05-13","cited_by_count":11,"area":"alignment"},{"id":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"area":"alignment"},{"id":"2607.05904","title":"More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges","created":"2026-07-07","cited_by_count":10,"area":"alignment"},{"id":"2404.01863","title":"Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models","created":"2024-04-02","cited_by_count":9,"area":"alignment"},{"id":"2505.12050","title":"AdaBoN: Adaptive Best-of-N Alignment","created":"2025-05-17","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":"2502.04354","title":"Reviving The Classics: Active Reward Modeling in Large Language Model Alignment","created":"2025-02-04","cited_by_count":8,"area":"alignment"},{"id":"2503.06810","title":"Mitigating Preference Hacking in Policy Optimization with Pessimism","created":"2025-03-10","cited_by_count":8,"area":"alignment"},{"id":"2406.15178","title":"Hybrid Alignment Training for Large Language Models","created":"2024-06-21","cited_by_count":7,"area":"alignment"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2406.15753","title":"The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret","created":"2024-06-22","cited_by_count":6,"area":"alignment"},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2506.05967","title":"Preference Learning for AI Alignment: a Causal Perspective","created":"2025-06-06","cited_by_count":6,"area":"alignment"},{"id":"2507.15507","title":"Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback","created":"2025-07-21","cited_by_count":6,"area":"alignment"},{"id":"2510.10963","title":"APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport","created":"2025-10-13","cited_by_count":6,"area":"alignment"},{"id":"2510.19050","title":"Rectifying Shortcut Behaviors in Preference-based Reward Learning","created":"2025-10-21","cited_by_count":6,"area":"alignment"},{"id":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"area":"alignment"},{"id":"2406.08124","title":"Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2410.04503","title":"LRHP: Learning Representations for Human Preferences via Preference Pairs","created":"2024-10-06","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2602.10623","title":"Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling","created":"2026-02-11","cited_by_count":5,"area":"alignment"},{"id":"2404.00978","title":"Prior Constraints-based Reward Model Training for Aligning Large Language Models","created":"2024-04-01","cited_by_count":4,"area":"alignment"},{"id":"2405.00438","title":"MetaRM: Shifted Distributions Alignment via Meta-Learning","created":"2024-05-01","cited_by_count":4,"area":"alignment"}],"next_cursor":"100"}