% Key papers for Steering and correcting LLM behavior (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2023_openassistant_68353,
  title = {{OpenAssistant Conversations - Democratizing Large Language Model Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73573},
}

@inproceedings{neurips2023_lima_67731,
  title = {{LIMA: Less Is More for Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72022},
}

@inproceedings{neurips2022_fine_64431,
  title = {{Fine-tuning language models to find agreement among humans with diverse preferences}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53005},
}

@inproceedings{neurips2023_principle_69480,
  title = {{Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70433},
}

@inproceedings{icml2024_fundamental_44114,
  title = {{Fundamental Limitations of Alignment in Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34338},
}

@inproceedings{neurips2023_beavertails_68995,
  title = {{BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73512},
}

@inproceedings{neurips2024_large_70741,
  title = {{Large Language Model Unlearning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96383},
}

@inproceedings{neurips2022_second_66257,
  title = {{Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53809},
}

@inproceedings{iclr2024_flask_33905,
  title = {{FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19170},
}

@inproceedings{iclr2024_rain_35292,
  title = {{RAIN: Your Language Models Can Align Themselves without Finetuning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17781},
}

@inproceedings{neurips2024_mission_73186,
  title = {{Mission Impossible: A Statistical Perspective on Jailbreaking LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94247},
}

@inproceedings{iclr2025_magpie_82056,
  title = {{Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29730},
}

@inproceedings{icml2024_self_45228,
  title = {{Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33224},
}

@inproceedings{neurips2024_self_72420,
  title = {{Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94936},
}

@inproceedings{neurips2024_aligning_74112,
  title = {{Aligning to Thousands of Preferences via System Message Generalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93423},
}

@inproceedings{aaai2025_approximated_8136,
  title = {{Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34519},
}

@inproceedings{neurips2024_bonbon_73398,
  title = {{BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94057},
}

@inproceedings{neurips2024_aligning_74567,
  title = {{Aligning Large Language Models with Representation Editing: A Control Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93018},
}

@inproceedings{neurips2024_prediction_70678,
  title = {{Prediction-Powered Ranking of Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96445},
}

@inproceedings{neurips2024_aligner_73623,
  title = {{Aligner: Efficient Alignment by Learning to Correct}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93865},
}

@inproceedings{neurips2024_alignment_74452,
  title = {{Alignment at Pre-training! Towards Native Alignment for Arabic LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93121},
}

@inproceedings{neurips2025_kl_78864,
  title = {{KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=j8XnFfTvXF},
}

@inproceedings{iclr2025_moral_81860,
  title = {{Moral Alignment for LLM Agents}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29923},
}

@inproceedings{aaai2026_safety_108433,
  title = {{Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40785},
}

@inproceedings{aaai2025_align_8077,
  title = {{Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34979},
}

@inproceedings{aaai2025_correcting_8543,
  title = {{Correcting Large Language Model Behavior via Influence Function}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33586},
}