% Key papers for Reward modeling for diverse preferences (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2024_rlaif_45650,
  title = {{RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32802},
}

@inproceedings{aaai2024_preference_6981,
  title = {{Preference Ranking Optimization for Human Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29865},
}

@inproceedings{neurips2017_teaching_56708,
  title = {{Teaching Machines to Describe Images with Natural Language Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9283},
}

@inproceedings{neurips2023_fine_67292,
  title = {{Fine-Grained Human Feedback Gives Better Rewards for Language Model Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72428},
}

@inproceedings{iclr2024_chain_33697,
  title = {{Chain of Hindsight aligns Language Models with Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19378},
}

@inproceedings{icml2024_weak_45034,
  title = {{Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33418},
}

@inproceedings{iclr2024_safe_34534,
  title = {{Safe RLHF: Safe Reinforcement Learning from Human Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18540},
}

@inproceedings{neurips2023_rrhf_67425,
  title = {{RRHF: Rank Responses to Align Language Models with Human Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72308},
}

@inproceedings{iclr2025_self_82608,
  title = {{Self-Play Preference Optimization for Language Model Alignment}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29189},
}

@inproceedings{icml2024_self_43250,
  title = {{Self-Rewarding Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35202},
}

@inproceedings{icml2023_the_43187,
  title = {{The Wisdom of Hindsight Makes Language Models Better Instruction Followers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24009},
}

@inproceedings{icml2024_position_45689,
  title = {{Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32763},
}

@inproceedings{icml2024_remax_44464,
  title = {{ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33988},
}

@inproceedings{neurips2024_inform_70358,
  title = {{InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96739},
}

@inproceedings{iclr2024_rlcd_35521,
  title = {{RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17552},
}

@inproceedings{iclr2025_language_84034,
  title = {{Language Models Learn to Mislead Humans via RLHF}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27791},
}

@inproceedings{iclr2025_taming_83270,
  title = {{Taming Overconfidence in LLMs: Reward Calibration in RLHF}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28542},
}

@inproceedings{iclr2025_towards_83371,
  title = {{Towards Federated RLHF with Aggregated Client Preference for LLMs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28445},
}

@inproceedings{iclr2024_distributional_33472,
  title = {{Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19603},
}

@inproceedings{iclr2024_language_33549,
  title = {{Language Model Self-improvement by Reinforcement Learning Contemplation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19526},
}

@inproceedings{icml2024_maxmin_43624,
  title = {{MaxMin-RLHF: Alignment with Diverse Human Preferences}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34828},
}

@inproceedings{icml2024_learning_44704,
  title = {{Learning Reward for Robot Skills Using Large Language Models via Self-Alignment}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33748},
}

@inproceedings{iclr2025_revolve_82738,
  title = {{REvolve: Reward Evolution with Large Language Models using Human Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29060},
}

@inproceedings{aaai2025_sequence_10746,
  title = {{Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34992},
}