Preference-Strength-Aware Self-Improving Alignment with Generative Preference Models.

@inproceedings{zhai-2025-preferencestrengthaware, author = {Yuanzhao Zhai and Zhuo Zhang and Cheng Yang and Kele Xu and Yue Yu and Wei Li and Hui Wang and Zenglin Xu and Dawei Feng and Bo Ding and Huaimin Wang}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Preference-Strength-Aware Self-Improving Alignment with Generative Preference Models}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {191--200}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3730063}, doi = {https://doi.org/10.1145/3726302.3730063} }