RedOne：揭示社交網絡服務中領域特定大語言模型的後訓練機制

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services

July 13, 2025

作者: Fei Zhao, Chonggang Lu, Yue Wang, Zheyong Xie, Ziyan Liu, Haofu Qian, JianZhao Huang, Fangcheng Shi, Zijie Meng, Hongcheng Guo, Mingqian He, Xinze Lyu, Yiming Lu, Ziyang Xiang, Zheyu Ye, Chengqiang Lu, Zhe Xu, Yi Wu, Yao Hu, Yan Gao, Jun Fan, Xiaolong Jiang, Weiting Liu, Boyang Wang, Shaosheng Cao

cs.AI

摘要

作爲現代信息傳播的主要媒介，社交網絡服務（SNS）經歷了快速增長，這對平臺內容管理和互動質量提升提出了重大挑戰。近年來，大型語言模型（LLMs）的發展提供了潛在的解決方案，但現有研究多聚焦於孤立任務，不僅在單一場景下數據擴展的效益遞減，且難以靈活適應多樣的現實情境。爲應對這些挑戰，我們引入了RedOne，這是一款專爲SNS設計的領域特定LLM，旨在突破單任務基線的性能瓶頸，並爲SNS建立一個全面的基礎。RedOne通過持續預訓練、監督微調和偏好優化的三階段訓練策略開發，利用大規模真實世界數據集。通過廣泛實驗，RedOne保持了強大的通用能力，在8項主要SNS任務上平均提升達14.02%，在SNS雙語評估基準上提升7.56%，相較於基礎模型。此外，通過在線測試，RedOne在有害內容檢測中的曝光率降低了11.23%，在帖子瀏覽搜索中的點擊頁面率提升了14.95%，相比於單任務微調的基線模型。這些結果確立了RedOne作爲一款針對SNS的強健領域特定LLM，展示了在各種任務上的優秀泛化能力以及在現實場景中的廣闊應用前景。

English

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 finetuned 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.