When & How to Write for Personalized Demand-aware Query Rewriting in Video Search

TL;DR

This paper introduces WeWrite, a personalized query rewriting framework for video search that improves relevance and efficiency by intelligently determining when and how to rewrite queries using large language models.

Contribution

The paper presents a novel framework combining automated sample mining, hybrid training, and low-latency deployment for personalized query rewriting in video search.

Findings

Increases click-through video volume by 1.07%

Reduces query reformulation rate by 2.97%

Demonstrates effectiveness through large-scale online A/B testing

Abstract

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%.