{"total":37,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"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":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"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":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"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":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2401.16635","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","created":"2024-01-30","cited_by_count":44,"area":"alignment"},{"id":"2203.07472","title":"Uncertainty Estimation for Language Reward Models","created":"2022-03-14","cited_by_count":37,"area":"alignment"},{"id":"2406.00654","title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","created":"2024-06-02","cited_by_count":20,"area":"alignment"},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2410.11236","title":"Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling","created":"2024-10-15","cited_by_count":14,"area":"alignment"},{"id":"2406.04854","title":"Uncertainty Aware Learning for Language Model Alignment","created":"2024-06-07","cited_by_count":13,"area":"alignment"},{"id":"2412.11803","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","created":"2024-12-16","cited_by_count":13,"area":"alignment"},{"id":"2510.20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","created":"2025-10-23","cited_by_count":13,"area":"alignment"},{"id":"2106.04316","title":"Exploration and preference satisfaction trade-off in reward-free learning","created":"2021-06-08","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":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"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":"2603.24124","title":"The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation","created":"2026-03-25","cited_by_count":4,"area":"alignment"},{"id":"2503.12528","title":"Investigating Human-Aligned Large Language Model Uncertainty","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2606.11201","title":"To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending","created":"2026-04-22","cited_by_count":2,"area":"alignment"},{"id":"2503.22480","title":"Probabilistic Uncertain Reward Model","created":"2025-03-28","cited_by_count":1,"area":"alignment"},{"id":"2504.14838","title":"Establishing Reliability Metrics for Reward Models in Large Language Models","created":"2025-04-21","cited_by_count":1,"area":"alignment"},{"id":"2606.09073","title":"A Unifying Lens on Reward Uncertainty in RLHF","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2205.07882","title":"Aligning Robot Representations with Humans","created":"2022-05-15","cited_by_count":0,"area":"alignment"},{"id":"2510.25884","title":"Approximating Human Preferences Using a Multi-Judge Learned System","created":"2025-10-29","cited_by_count":0,"area":"alignment"},{"id":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2604.14651","title":"CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2607.14480","title":"Lower-Resource, Higher Scores: Language Bias in LLM Evaluators","created":"2026-07-16","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":"2609.34506","title":"Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.15008","title":"Can You Trust Your Preference Models? Stackelberg Games for Alignment","created":"2026-10-10","cited_by_count":0,"area":"alignment"}],"next_cursor":null}