@inproceedings{zhao-etal-2025-redone,
    title = "{R}ed{O}ne: Revealing Domain-specific {LLM} Post-Training in Social Networking Services",
    author = "Zhao, Fei  and
      Lu, Chonggang  and
      Wangyue  and
      Xie, Zheyong  and
      Liu, Ziyan  and
      Qian, Haofu  and
      Huang, Jianzhao  and
      Shi, Fangcheng  and
      Meng, Zijie  and
      Guo, Hongcheng  and
      He, Mingqian  and
      Lyu, Xinze  and
      Ye, Zheyu  and
      Liu, Weiting  and
      Wang, Boyang  and
      Cao, Shaosheng",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.180/",
    pages = "2648--2674",
    ISBN = "979-8-89176-333-3",
    abstract = "As a primary medium for modern information dissemination, social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement. Recently, the development of large language models (LLMs) has offered potential solutions but existing studies focus on isolated tasks, which not only encounter diminishing benefit from the data scaling within individual scenarios but also fail to flexibly adapt to diverse real-world context. To address these challenges, we introduce RedOne, a domain-specific LLM designed to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for the SNS. RedOne was developed through a three-stage training strategy consisting of continue pretraining, supervised fine-tuning, and preference optimization, using a large-scale real-world dataset. Through extensive experiments, RedOne maintains strong general capabilities, and achieves an average improvement up to 14.02{\%} across 8 major SNS tasks and 7.56{\%} in SNS bilingual evaluation benchmark, compared with base models. Furthermore, through online testing, RedOne reduced the exposure rate in harmful content detection by 11.23{\%} and improved the click page rate in post-view search by 14.95{\%} compared with single-tasks baseline models. These results establish RedOne as a robust domain-specific LLM for SNS, demonstrating excellent generalization across various tasks and promising applicability in real-world scenarios."
}