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

TL;DR

RedOne is a domain-specific large language model tailored for social networking services, developed through a multi-stage training process, that significantly improves performance across multiple SNS tasks and real-world applications.

Contribution

The paper introduces RedOne, a novel domain-specific LLM for SNS, with a three-stage training strategy that enhances multi-task performance and real-world applicability.

Findings

RedOne improves average task performance by up to 14.02%.

RedOne reduces harmful content exposure rate by 11.23%.

RedOne increases click page rate by 14.95%.

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 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.