通过智能时机与风格适配，提升视频搜索的个性化重写效果
When & How to Write for Personalized Demand-aware Query Rewriting in Video Search
- 根据用户行为自动识别需个性化重写的场景
- 结合监督微调与策略优化，使大模型输出适配检索系统
- 部署低延迟架构，适合大规模视频平台使用
在视频搜索系统中，用户历史行为可提供丰富上下文以识别搜索意图并解决歧义。然而，传统利用隐式历史特征的方法常面临信号稀释和反馈延迟问题。为此，我们提出 WeWrite，一种新型个性化需求感知查询重写框架。具体而言，WeWrite 解决三个关键挑战：(1) 何时重写：基于后验的自动化挖掘策略从用户日志中提取高质量样本，识别出必须个性化重写的场景；(2) 如何重写：采用监督微调（SFT）与组相对策略优化（GRPO）相结合的混合训练范式，使大语言模型输出风格与检索系统对齐；(3) 部署：采用并行‘假召回’架构实现低延迟。在大型视频平台上的在线A/B测试表明，WeWrite使点击播放时长超过10秒的视频总量（VV>10s）提升1.07%，查询重写率降低2.97%。
原文摘要 · Abstract (English)
In video search systems, user historical behaviors provide rich context for identifying search intent and resolving ambiguity. However, traditional methods utilizing implicit history features often suffer from signal dilution and delayed feedback. To address these challenges, we propose WeWrite, a novel Personalized Demand-aware Query Rewriting framework. Specifically, WeWrite tackles three key challenges: (1) When to Write: An automated posterior-based mining strategy extracts high-quality samples from user logs, identifying scenarios where personalization is strictly necessary; (2) How to Write: A hybrid training paradigm combines Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO) to align the LLM's output style with the retrieval system; (3) Deployment: A parallel "Fake Recall" architecture ensures low latency. Online A/B testing on a large-scale video platform demonstrates that WeWrite improves the Click-Through Video Volume (VV$>$10s) by 1.07% and reduces the Query Reformulation Rate by 2.97%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。