{"total":94,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"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":"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":"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":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"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":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2405.01525","title":"FLAME: Factuality-Aware Alignment for Large Language Models","created":"2024-05-02","cited_by_count":47,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"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":"2407.09499","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","created":"2024-06-12","cited_by_count":39,"area":"alignment"},{"id":"2402.13210","title":"Bayesian Reward Models for LLM Alignment","created":"2024-02-20","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":"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":"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":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"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":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2501.08617","title":"RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation","created":"2025-01-15","cited_by_count":15,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"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":"2506.03690","title":"Robust Preference Optimization via Dynamic Target Margins","created":"2025-06-04","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":"2505.18126","title":"Reward Model Overoptimisation in Iterated RLHF","created":"2025-05-23","cited_by_count":12,"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":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"area":"alignment"},{"id":"2602.01750","title":"Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2506.10054","title":"Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs","created":"2025-06-11","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":"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":"2407.15229","title":"A Practical Analysis of Human Alignment with *PO","created":"2024-07-21","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":"2505.12843","title":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","created":"2025-05-19","cited_by_count":7,"area":"alignment"},{"id":"2603.10535","title":"Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning","created":"2026-03-11","cited_by_count":7,"area":"alignment"},{"id":"2603.18736","title":"CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks","created":"2026-03-19","cited_by_count":7,"area":"alignment"},{"id":"2405.16681","title":"Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization","created":"2024-05-26","cited_by_count":6,"area":"alignment"},{"id":"2502.00814","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","created":"2025-02-02","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":"2510.19050","title":"Rectifying Shortcut Behaviors in Preference-based Reward Learning","created":"2025-10-21","cited_by_count":6,"area":"alignment"},{"id":"2510.23751","title":"Debiasing Reward Models by Representation Learning with Guarantees","created":"2025-10-27","cited_by_count":6,"area":"alignment"},{"id":"2511.12573","title":"Mitigating Length Bias in RLHF through a Causal Lens","created":"2025-11-16","cited_by_count":6,"area":"alignment"},{"id":"2601.18533","title":"From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation","created":"2026-01-26","cited_by_count":6,"area":"alignment"},{"id":"2503.04793","title":"Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference","created":"2025-03-01","cited_by_count":5,"area":"alignment"},{"id":"2504.06020","title":"Information-Theoretic Reward Decomposition for Generalizable RLHF","created":"2025-04-08","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":"2602.19416","title":"IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking","created":"2026-02-23","cited_by_count":5,"area":"alignment"},{"id":"2503.07426","title":"RePO: Understanding Preference Learning Through ReLU-Based Optimization","created":"2025-03-10","cited_by_count":4,"area":"alignment"},{"id":"2504.13134","title":"Energy-Based Reward Models for Robust Language Model Alignment","created":"2025-04-17","cited_by_count":4,"area":"alignment"},{"id":"2512.17375","title":"AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens","created":"2025-12-19","cited_by_count":4,"area":"alignment"},{"id":"2602.08829","title":"WildReward: Learning Reward Models from In-the-Wild Human Interactions","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2605.17602","title":"AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment","created":"2026-05-17","cited_by_count":3,"area":"alignment"},{"id":"2607.01830","title":"Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling","created":"2026-07-02","cited_by_count":3,"area":"alignment"},{"id":"2503.03122","title":"The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models","created":"2025-03-05","cited_by_count":2,"area":"alignment"},{"id":"2511.09864","title":"Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models","created":"2025-11-13","cited_by_count":2,"area":"alignment"},{"id":"2603.12795","title":"SteerRM: Debiasing Reward Models via Sparse Autoencoders","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2606.03131","title":"HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2606.09043","title":"DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity","created":"2026-06-08","cited_by_count":2,"area":"alignment"},{"id":"2609.00213","title":"Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning","created":"2026-08-31","cited_by_count":2,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2412.16475","title":"When Can Proxies Improve the Sample Complexity of Preference Learning?","created":"2024-12-21","cited_by_count":1,"area":"alignment"},{"id":"2503.22480","title":"Probabilistic Uncertain Reward Model","created":"2025-03-28","cited_by_count":1,"area":"alignment"},{"id":"2506.00152","title":"Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective","created":"2025-05-30","cited_by_count":1,"area":"alignment"},{"id":"2506.08681","title":"Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling","created":"2025-06-10","cited_by_count":1,"area":"alignment"},{"id":"2510.05526","title":"Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2601.21350","title":"Factored Causal Representation Learning for Robust Reward Modeling in RLHF","created":"2026-01-29","cited_by_count":1,"area":"alignment"},{"id":"2601.22083","title":"Latent Adversarial Regularization for Offline Preference Optimization","created":"2026-01-29","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":"2606.09711","title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2607.16240","title":"Normalized Rewards for Preference Optimization","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2412.16378","title":"REFA: Reference Free Alignment for multi-preference optimization","created":"2024-12-20","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":"2507.07855","title":"DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and its Loss' Convexity is Dispensable)","created":"2025-07-10","cited_by_count":0,"area":"alignment"},{"id":"2508.14391","title":"Hallucination-Resistant Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement","created":"2025-08-20","cited_by_count":0,"area":"alignment"},{"id":"2604.13833","title":"Robust Reward Modeling for Large Language Models via Causal Decomposition","created":"2026-04-15","cited_by_count":0,"area":"alignment"},{"id":"2604.27495","title":"Debiasing Reward Models via Causally Motivated Inference-Time Intervention","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.10981","title":"$\\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin","created":"2026-05-09","cited_by_count":0,"area":"alignment"},{"id":"2609.00699","title":"Patterning in Practice: Debiasing Reward Models with Susceptibilities","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.32720","title":"BiasReducer: Adaptive Bias Mitigation for Reward Models","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.33221","title":"RMB: Reward Model Boosting Mitigates Reward Hacking","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.34718","title":"Quality Determines Direction, Length Shapes Magnitude: Length Control for Open-Ended Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.35044","title":"BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.17062","title":"Gradient Routing Localizes and Removes Unintended Behaviors in RL","created":"2026-10-12","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}