RL from Human Feedback

RL: Reinforcement Learning

Ask about this topic

Overview

RLHF studies how to use human judgments and interventions to teach AI systems which responses or actions are desirable, especially when goals are hard to specify with a fixed reward. Common approaches learn reward models from pairwise comparisons and optimize policies with PPO or GRPO, while methods such as Direct Preference Optimization learn directly from preference pairs; active learning and online feedback aim to reduce the data required. Research spans language-model alignment and benchmarks such as AlpacaEval and MT-Bench, as well as robot learning from corrections and demonstrations. A central challenge is that feedback can be noisy, biased, or diverse, and optimizing an imperfect reward can cause reward hacking, so work increasingly studies uncertainty, robustness, fairness, and how to measure real-world improvement rather than proxy scores alone.

Latest papers

CardsList

128 papers10 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

  1. Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback

    Mar 30, 2026Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban +2Multi-Agent Reinforcement LearningOffline MARL

    MPI-SWS · University of Warwick · Visa

  2. Distributionally Robust Token Optimization in RLHF

    Mar 27, 2026Yeping Jin, Jiaming Hu, Ioannis Ch. PaschalidisLanguage Model RobustnessReasoning Consistency in Language Models

    Department of System Engineering Boston University, Boston, MA 02215, USA · Department of Math & Statistics Boston University, Boston, MA 02215, USA

  3. Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Control

    Mar 26, 2026Zhuoli Zhuang, Yu-Cheng Chang, Yu-Kai Wang +2RL for Autonomous DrivingReinforcement Learning

    University of Technology Sydney

  4. Unbiased Reward Modeling from Implicit Feedback for LLM Alignment

    Mar 24, 2026Hao Wang, Haocheng Yang, Licheng Pan +7Reward ModelingLLM Alignment

    Peking University · Xiaohongshu Inc. · National University of Singapore +1

  5. Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling

    Mar 23, 2026Young Hyun Cho, Will Wei SunPrivacy-Preserving MLPrivacy-Preserving Language Models

    Purdue University

  6. Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences

    Mar 20, 2026Ming Shi, Yingbin Liang, Ness B. Shroff +1Preference-Based RLRL from Human Feedback

    Department of Electrical Engineering, University at Buffalo, Buffalo, NY 14260, USA · Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH 43210, USA · Department of Electrical and Computer Engineering and Computer Science and Engineering, The Ohio State University, Columbus, OH 43210, USA +1

  7. CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks

    Mar 19, 2026Hao Wang, Licheng Pan, Zhichao Chen +7Reward ModelingRL from Human Feedback

    Peking University · Xiaohongshu Inc. · Zhejiang University

  8. Efficient Exploration at Scale

    Mar 18, 2026Seyed Mohammad Asghari, Chris Chute, Vikranth Dwaracherla +5RL from Human FeedbackData-Efficient Learning

    The Efficient Agent Team, Google DeepMind

  9. Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences

    Mar 17, 2026Quan ChengLLM AlignmentRL from Human Feedback

    Tsinghua University

  10. Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback

    Mar 13, 2026Gihoon Kim, Euntai KimPreference LearningRL from Human Feedback

    Yonsei University · Korea Institute of Science and Technology

  11. ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

    Mar 10, 2026Davit Melikidze, Marian Schneider, Jessica Lam +4Data SelectionActive Learning

    ETH Zurich · Institute of Neuroinformatics, University of Zurich and ETH Zurich · ETH AI Center

  12. Aligning to Illusions: Choice Blindness in Human and AI Feedback

    Mar 9, 2026Wenbin WuRL from Human FeedbackBias in LLM-as-a-Judge

    Cambridge Judge Business School, University of Cambridge, UK

  13. Why Is RLHF Alignment Shallow? A Gradient Analysis

    Mar 5, 2026Robin YoungLLM AlignmentLLM Safety Alignment

    Department of Computer Science and Technology University of Cambridge Cambridge, UK

  14. Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

    Mar 4, 2026Lei Huang, Xiang Cheng, Chenxiao Zhao +6RL ExplorationRL for Language Models

    Harbin Institute of Technology · Xiaohongshu Inc.

  15. PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems

    Mar 3, 2026Sudip BhujelPrivacy-Preserving Language ModelsRL from Human Feedback

    Department of Computer Science, University of Kentucky, Lexington, KY, USA

  16. Human Supervision as an Information Bottleneck: A Unified Theory of Error Floors in Human-Guided Learning

    Feb 26, 2026Alejandro Rodriguez DominguezInformation BottleneckLearning with Noisy Labels

    Miralta Finance Bank S.A., Spain · Department of Computer Science, University of Reading, UK

  17. Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive

    Feb 26, 2026Radha SarmaAI GovernanceAI Alignment

  18. Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences

    Feb 26, 2026Junghyun Lee, Minju Hong, Kwang-Sung Jun +2Regret Minimization in RLPreference-Based RL

    KAIST AI · KAIST EE · POSTECH CSE/AI

  19. RLHFless: Serverless Computing for Efficient RLHF

    Feb 26, 2026Rui Wei, Hanfei Yu, Shubham Jain +5Efficient Language Model TrainingRL from Human Feedback

    Stevens Institute of Technology · Northeastern University · Stony Brook University +1

  20. Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual

    Feb 25, 2026Yining Li, Peizhong Ju, Ness ShroffLLM Safety AlignmentRL from Human Feedback

    The Ohio State University · University of Kentucky

  21. Generalisation of RLHF under Reward Shift and Clipped KL Regularisation

    Feb 25, 2026Kenton Tang, Yuzhu Chen, Fengxiang HeRL from Human FeedbackGeneralization in RL

    University of Edinburgh · University of Science and Technology of China

  22. Sample-Efficient Learning with Online Expert Correction for Autonomous Catheter Steering in Endovascular Bifurcation Navigation

    Feb 23, 2026Hao Wang, Tianliang Yao, Bo Lu +4Robotic Endovascular InterventionRL for Robotics

    Department of Control Science and Engineering, College of Electronics and Information Engineering, and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai 200092, China · Department of Electronic Engineering, Faculty of Engineering, The Chinese University of Hong Kong, Hong Kong SAR 999077, China · Robotics and Microsystems Center, School of Mechanical and Electric Engineering, Soochow University, Suzhou, Jiangsu 215131, China +3

  23. IR3^3: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking

    Feb 23, 2026Mohammad Beigi, Ming Jin, Junshan Zhang +3Reward HackingReinforcement Learning

    UC Davis · Virginia Tech · Salesforce +1

  24. Enhancing Goal Inference via Correction Timing

    Feb 20, 2026Anjiabei Wang, Shuangge Wang, Tesca FitzgeraldRobot LearningHuman-Robot Collaboration

    Yale University, New Haven, CT, United States

  25. Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards

    Feb 20, 2026Johannes Ackermann, Michael Noukhovitch, Takashi Ishida +1Reward HackingReinforcement Learning with Verifiable Rewards

    The University of Tokyo · Mila · RIKEN AIP

  26. Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models

    Feb 7, 2026Yankai Yang, Yancheng Long, Hongyang Wei +12Reward ModelingMultimodal Reward Modeling

    Harbin Institute of Technology, Shenzhen. · Kuaishou Technology.

  27. Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking

    Feb 2, 2026Mohammad Beigi, Ming Jin, Junshan Zhang +2Adversarial TrainingReward Hacking

    Department of Computer Science, University of California, Davis, USA · Virginia Tech, Blacksburg, USA · Meta AI Research.

  28. Adaptive Margin RLHF via Preference over Preferences

    Sep 26, 2025Yaswanth Chittepu, Prasann Singhal, Greg Durrett +1Pairwise Preference LearningReward Modeling

    University of Massachusetts Amherst · University of Texas at Austin

  29. Aligning Audio Captions with Human Preferences

    Sep 18, 2025Kartik Hegde, Rehana Mahfuz, Yinyi Guo +1Reward ModelingAudio-Language Models

    Qualcomm Technologies, Inc., India · Qualcomm Technologies, Inc., USA

  30. TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback

    Aug 4, 2025Lei Pang, Jun Luo, Ruinan JinImportance Sampling for RLRL for Language Models

    Peking University Beijing, China · The Ohio State University Columbus, USA · Shugu Yuntai Technology Co., Ltd. +1