% Key papers for Reward model design and preference models (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2024_eureka_34104,
  title = {{Eureka: Human-Level Reward Design via Coding Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18971},
}

@inproceedings{aaai2017_coactive_104552,
  title = {{Coactive Critiquing: Elicitation of Preferences and Features}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10929},
}

@inproceedings{aaai2018_an_100985,
  title = {{An Axiomatization of the Eigenvector and Katz Centralities}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11435},
}

@inproceedings{icml2024_ai_45119,
  title = {{AI Alignment with Changing and Influenceable Reward Functions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33333},
}

@inproceedings{neurips2019_reward_58916,
  title = {{Reward Constrained Interactive Recommendation with Natural Language Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14421},
}

@inproceedings{neurips2025_vton_79121,
  title = {{VTON-VLLM: Aligning Virtual Try-On Models with Human Preferences}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=ltOnam1gY7},
}

@inproceedings{neurips2024_helpsteer_72044,
  title = {{HelpSteer 2: Open-source dataset for training top-performing reward models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97706},
}

@inproceedings{iclr2025_helpsteer2_81866,
  title = {{HelpSteer2-Preference: Complementing Ratings with Preferences}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29917},
}

@inproceedings{aaai2024_facetcrs_5946,
  title = {{FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28794},
}

@inproceedings{icml2025_aligning_47513,
  title = {{Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45083},
}

@inproceedings{neurips2024_distributional_70267,
  title = {{Distributional Preference Alignment of LLMs via Optimal Transport}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96822},
}

@inproceedings{iclr2024_tool_34802,
  title = {{Tool-Augmented Reward Modeling}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18272},
}

@inproceedings{neurips2024_preference_71189,
  title = {{Preference Alignment with Flow Matching}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96042},
}

@inproceedings{neurips2025_inference_78695,
  title = {{Inference-Time Reward Hacking in Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=hSX7Dd8dxy},
}

@inproceedings{neurips2025_helpsteer3_79112,
  title = {{HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=lovsIkZLnI},
}

@inproceedings{aaai2025_legend_9669,
  title = {{LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34937},
}

@inproceedings{aaai2025_maple_9833,
  title = {{MAPLE: A Framework for Active Preference Learning Guided by Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34964},
}

@inproceedings{aaai2025_priority2reward_10251,
  title = {{PRIORITY2REWARD: Incorporating Healthworker Preferences for Resource Allocation Planning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35375},
}

@inproceedings{aaai2025_synapse_10659,
  title = {{SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34965},
}

@inproceedings{icml2025_beyond_47492,
  title = {{Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45103},
}

@inproceedings{neurips2024_deep_72295,
  title = {{Deep Bayesian Active Learning for Preference Modeling in Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95050},
}

@inproceedings{neurips2024_value_73255,
  title = {{Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97583},
}

@inproceedings{neurips2025_bleuberi_78127,
  title = {{BLEUBERI: BLEU is a surprisingly effective reward for instruction following}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=bEYzeItoOH},
}