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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Fei, Lu, Chonggang, Wang, Yue, Xie, Zheyong, Liu, Ziyan, Qian, Haofu, Huang, JianZhao, Shi, Fangcheng, Meng, Zijie, Guo, Hongcheng, He, Mingqian, Lyu, Xinze, Lu, Yiming, Xiang, Ziyang, Ye, Zheyu, Lu, Chengqiang, Xu, Zhe, Wu, Yi, Hu, Yao, Gao, Yan, Fan, Jun, Jiang, Xiaolong, Liu, Weiting, Wang, Boyang, Cao, Shaosheng
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Social and Information Networks
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866911205377966080
author	Zhao, Fei Lu, Chonggang Wang, Yue Xie, Zheyong Liu, Ziyan Qian, Haofu Huang, JianZhao Shi, Fangcheng Meng, Zijie Guo, Hongcheng He, Mingqian Lyu, Xinze Lu, Yiming Xiang, Ziyang Ye, Zheyu Lu, Chengqiang Xu, Zhe Wu, Yi Hu, Yao Gao, Yan Fan, Jun Jiang, Xiaolong Liu, Weiting Wang, Boyang Cao, Shaosheng
author_facet	Zhao, Fei Lu, Chonggang Wang, Yue Xie, Zheyong Liu, Ziyan Qian, Haofu Huang, JianZhao Shi, Fangcheng Meng, Zijie Guo, Hongcheng He, Mingqian Lyu, Xinze Lu, Yiming Xiang, Ziyang Ye, Zheyu Lu, Chengqiang Xu, Zhe Wu, Yi Hu, Yao Gao, Yan Fan, Jun Jiang, Xiaolong Liu, Weiting Wang, Boyang Cao, Shaosheng
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2507_10605
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services Zhao, Fei Lu, Chonggang Wang, Yue Xie, Zheyong Liu, Ziyan Qian, Haofu Huang, JianZhao Shi, Fangcheng Meng, Zijie Guo, Hongcheng He, Mingqian Lyu, Xinze Lu, Yiming Xiang, Ziyang Ye, Zheyu Lu, Chengqiang Xu, Zhe Wu, Yi Hu, Yao Gao, Yan Fan, Jun Jiang, Xiaolong Liu, Weiting Wang, Boyang Cao, Shaosheng Machine Learning Artificial Intelligence Social and Information Networks 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.
title	RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services
topic	Machine Learning Artificial Intelligence Social and Information Networks
url	https://arxiv.org/abs/2507.10605