{"total":38,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"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":"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":"2310.05199","title":"Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback","created":"2023-10-08","cited_by_count":78,"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":"2407.00617","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning","created":"2024-06-30","cited_by_count":45,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29,"area":"alignment"},{"id":"2310.11971","title":"Improving Generalization of Alignment with Human Preferences through Group Invariant Learning","created":"2023-10-18","cited_by_count":25,"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":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2310.07932","title":"What Matters to You? Towards Visual Representation Alignment for Robot Learning","created":"2023-10-11","cited_by_count":14,"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":"2503.00539","title":"Distributionally Robust Reinforcement Learning with Human Feedback","created":"2025-03-01","cited_by_count":12,"area":"alignment"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","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":"2410.12491","title":"Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning","created":"2024-10-16","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":"2505.20556","title":"Learning a Pessimistic Reward Model in RLHF","created":"2025-05-26","cited_by_count":5,"area":"alignment"},{"id":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2512.23067","title":"The Reward Model Selection Crisis in Personalized Alignment","created":"2025-12-28","cited_by_count":3,"area":"alignment"},{"id":"2603.04861","title":"Causally Robust Reward Learning from Reason-Augmented Preference Feedback","created":"2026-03-05","cited_by_count":2,"area":"alignment"},{"id":"2604.08326","title":"ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection","created":"2026-04-09","cited_by_count":2,"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":"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":"2605.16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2306.13004","title":"Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?","created":"2023-06-22","cited_by_count":0,"area":"alignment"},{"id":"2407.14681","title":"Value Internalization: Learning and Generalizing from Social Reward","created":"2024-07-19","cited_by_count":0,"area":"alignment"},{"id":"2408.05610","title":"Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations","created":"2024-08-10","cited_by_count":0,"area":"alignment"},{"id":"2412.07990","title":"Adaptive Querying for Reward Learning from Human Feedback","created":"2024-12-11","cited_by_count":0,"area":"alignment"},{"id":"2501.00911","title":"Aligning LLMs with Domain Invariant Reward Models","created":"2025-01-01","cited_by_count":0,"area":"alignment"},{"id":"2602.19423","title":"Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy","created":"2026-02-23","cited_by_count":0,"area":"alignment"},{"id":"2605.21822","title":"Implicit Safety Alignment from Crowd Preferences","created":"2026-05-20","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":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2610.04054","title":"Reward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Models","created":"2026-10-02","cited_by_count":0,"area":"alignment"}],"next_cursor":null}