{"total":23,"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":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"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":"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":"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":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53,"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":"2407.03038","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","created":"2024-07-03","cited_by_count":13,"area":"alignment"},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2112.11230","title":"Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions","created":"2021-12-20","cited_by_count":10,"area":"alignment"},{"id":"2502.18699","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","created":"2025-02-25","cited_by_count":10,"area":"alignment"},{"id":"2203.13553","title":"Preprocessing Reward Functions for Interpretability","created":"2022-03-25","cited_by_count":7,"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":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2310.08164","title":"Interpreting Learned Feedback Patterns in Large Language Models","created":"2023-10-12","cited_by_count":4,"area":"alignment"},{"id":"2210.01007","title":"Reward Learning with Trees: Methods and Evaluation","created":"2022-10-03","cited_by_count":2,"area":"alignment"},{"id":"2402.04856","title":"Explaining Learned Reward Functions with Counterfactual Trajectories","created":"2024-02-07","cited_by_count":1,"area":"alignment"},{"id":"2305.16924","title":"Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback","created":"2023-05-26","cited_by_count":0,"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":"2608.19748","title":"Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification","created":"2026-08-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}