% Key papers for Robust and calibrated DPO (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages. @inproceedings{cvpr2025_popen_27196, title = {{POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/33340}, } @inproceedings{neurips2024_cal_70496, title = {{Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/96611}, } @inproceedings{aaai2023_cop_3267, title = {{CoP: Factual Inconsistency Detection by Controlling the Preference}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2023}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/26589}, } @inproceedings{neurips2024_unpacking_71548, title = {{Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/95717}, } @inproceedings{neurips2024_noise_71644, title = {{Noise Contrastive Alignment of Language Models with Explicit Rewards}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/95633}, } @inproceedings{neurips2025_less_77159, title = {{Less is More: Improving LLM Alignment via Preference Data Selection}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=R2ZJSjLDJC}, } @inproceedings{neurips2024_speechalign_72230, title = {{SpeechAlign: Aligning Speech Generation to Human Preferences}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/95112}, } @inproceedings{neurips2024_robust_73001, title = {{Robust Reinforcement Learning from Corrupted Human Feedback}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/94419}, } @inproceedings{neurips2024_panacea_73292, title = {{Panacea: Pareto Alignment via Preference Adaptation for LLMs}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/94149}, } @inproceedings{neurips2025_simplicity_76465, title = {{Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=JbvSQm5h1l}, } @inproceedings{icml2024_grath_44881, title = {{GRATH: Gradual Self-Truthifying for Large Language Models}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2024}, url = {https://icml.cc/virtual/2024/poster/33571}, } @inproceedings{icml2026_lilo_55485, title = {{LILO: Bayesian Optimization with Natural Language Feedback}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=zVrbE9ZtEU}, } @inproceedings{aaai2025_self_10718, title = {{Self-Evolutionary Large Language Models Through Uncertainty-Enhanced Preference Optimization}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34724}, } @inproceedings{icml2024_provably_45793, title = {{Provably Robust DPO: Aligning Language Models with Noisy Feedback}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2024}, url = {https://icml.cc/virtual/2024/poster/32659}, } @inproceedings{icml2025_test_46416, title = {{Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2025}, url = {https://icml.cc/virtual/2025/poster/46149}, } @inproceedings{icml2025_principled_48707, title = {{Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2025}, url = {https://icml.cc/virtual/2025/poster/43915}, } @inproceedings{neurips2023_preference_66886, title = {{Preference-grounded Token-level Guidance for Language Model Fine-tuning}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2023}, url = {https://nips.cc/virtual/2023/poster/72756}, } @inproceedings{neurips2024_improving_70491, title = {{Improving Context-Aware Preference Modeling for Language Models}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/96617}, } @inproceedings{neurips2024_humor_74397, title = {{Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/97450}, } @inproceedings{neurips2025_implicit_80225, title = {{Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=xUx2B2NHvj}, } @inproceedings{aaai2026_align_106344, title = {{Align³GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/38651}, } @inproceedings{aaai2026_ranklist_107279, title = {{RankList – a Listwise Preference Learning Framework for Predicting Subjective Preferences}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/39631}, }