% Key papers for Theory of RLHF (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2017_interactive_36234,
  title = {{Interactive Learning from Policy-Dependent Human Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/846},
}

@inproceedings{iclr2023_is_32138,
  title = {{Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10970},
}

@inproceedings{cvpr2024_using_25177,
  title = {{Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30065},
}

@inproceedings{icml2023_scaling_42564,
  title = {{Scaling Laws for Reward Model Overoptimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24924},
}

@inproceedings{aaai2021_learning_894,
  title = {{Learning Rewards From Linguistic Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/06002-learning-rewards-from-linguistic-feedback/},
}

@inproceedings{aaai2021_reinforcement_1255,
  title = {{Reinforcement Learning with Trajectory Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/07288-reinforcement-learning-with-trajectory-feedback/},
}

@inproceedings{icml2023_principled_42020,
  title = {{Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25211},
}

@inproceedings{aaai2023_the_4798,
  title = {{The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25740},
}

@inproceedings{aaai2020_mega_102178,
  title = {{Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6040},
}

@inproceedings{neurips2024_personalizing_73302,
  title = {{Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94141},
}

@inproceedings{iclr2024_text2reward_35457,
  title = {{Text2Reward: Reward Shaping with Language Models for Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17616},
}

@inproceedings{iclr2022_reward_31219,
  title = {{Reward Uncertainty for Exploration in Preference-based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6956},
}

@inproceedings{neurips2024_scaling_73975,
  title = {{Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93540},
}

@inproceedings{icml2024_rl_44680,
  title = {{RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33772},
}

@inproceedings{neurips2023_inverse_69006,
  title = {{Inverse Preference Learning: Preference-based RL without a Reward Function}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70866},
}

@inproceedings{aaai2020_what_101233,
  title = {{What Is It You Really Want of Me? Generalized Reward Learning with Biased Beliefs about Domain Dynamics}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5630},
}

@inproceedings{aaai2024_learning_6471,
  title = {{Learning Optimal Advantage from Preferences and Mistaking It for Reward}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28870},
}

@inproceedings{neurips2023_sequential_67846,
  title = {{Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71915},
}

@inproceedings{neurips2022_non_64745,
  title = {{Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55112},
}

@inproceedings{neurips2024_adaptive_71373,
  title = {{Adaptive Preference Scaling for Reinforcement Learning with Human Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95876},
}

@inproceedings{neurips2024_online_72346,
  title = {{Online Iterative Reinforcement Learning from Human Feedback with General Preference Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95002},
}

@inproceedings{aaai2024_esrl_5785,
  title = {{ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29878},
}

@inproceedings{iclr2024_zeroth_34504,
  title = {{Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18570},
}

@inproceedings{iclr2024_uni_34606,
  title = {{Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18468},
}

@inproceedings{icml2024_warm_45528,
  title = {{WARM: On the Benefits of Weight Averaged Reward Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32924},
}

@inproceedings{neurips2024_multi_74099,
  title = {{Multi-turn Reinforcement Learning with Preference Human Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93434},
}

@inproceedings{iclr2024_reward_34821,
  title = {{Reward Model Ensembles Help Mitigate Overoptimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18253},
}

@inproceedings{icml2024_dense_44976,
  title = {{Dense Reward for Free in Reinforcement Learning from Human Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33476},
}

@inproceedings{icml2026_how_52586,
  title = {{How RLHF Amplifies Sycophancy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=XN4pWKtA5h},
}

@inproceedings{neurips2024_one_73065,
  title = {{One-Shot Safety Alignment for Large Language Models via Optimal Dualization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94361},
}

@inproceedings{aaai2025_alleviating_8092,
  title = {{Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34552},
}

@inproceedings{aaai2025_duo_8627,
  title = {{DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33824},
}

@inproceedings{aaai2025_efficient_8924,
  title = {{Efficient and Robust Reinforcement Learning from Human Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35123},
}