@inproceedings{xiang-etal-2025-self,
    title = "Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models",
    author = "Xiang, Hao  and
      Yu, Bowen  and
      Lin, Hongyu  and
      Lu, Keming  and
      Lu, Yaojie  and
      Han, Xianpei  and
      He, Ben  and
      Sun, Le  and
      Zhou, Jingren  and
      Lin, Junyang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.473/",
    pages = "9073--9085",
    ISBN = "979-8-89176-256-5",
    abstract = "The key to effective alignment lies in high-quality preference data. Recent research has focused on automated alignment, which involves developing alignment systems with minimal human intervention. However, prior research has predominantly focused on developing data generation methods, while insufficient attention has been paid to quality control mechanisms and often produces inaccurate and unhelpful data, leading to unpredictable benefits during iterative optimization. In this paper, we present Self-Steering Optimization ($SSO$), an algorithm that autonomously generates high-quality preference data, eliminating manual annotation requirements. $SSO$ employs a specialized optimization objective to build a data generator from the policy model itself, which is used to produce accurate and on-policy data. We demonstrate $SSO${`}s effectiveness through comprehensive experiments on two series of models: Llama 3 and Qwen 2. Our evaluation across diverse benchmarks shows that $SSO$ consistently outperforms baselines in human preference alignment and reward optimization. Further analysis validates $SSO$ as a scalable framework for preference optimization, benefiting the advancement in automated alignment techniques."
}