QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search

TL;DR

QP-OneModel introduces a unified generative large language model for multi-task query understanding in SNS search, improving semantic comprehension, task performance, and generalization over traditional discriminative models.

Contribution

It reformulates heterogeneous query understanding tasks into a unified sequence generation framework with a progressive training strategy and generates intent descriptions to enhance downstream tasks.

Findings

Achieves 7.35% overall gain over discriminative baselines.

Boosts F1 scores in NER (+9.01%) and Term Weighting (+9.31%).

Surpasses a 32B model by 7.60% accuracy on unseen tasks.

Abstract

Query Processing (QP) bridges user intent and content supply in large-scale Social Network Service (SNS) search engines. Traditional QP systems rely on pipelines of isolated discriminative models (e.g., BERT), suffering from limited semantic understanding and high maintenance overhead. While Large Language Models (LLMs) offer a potential solution, existing approaches often optimize sub-tasks in isolation, neglecting intrinsic semantic synergy and necessitating independent iterations. Moreover, standard generative methods often lack grounding in SNS scenarios, failing to bridge the gap between open-domain corpora and informal SNS linguistic patterns, while struggling to adhere to rigorous business definitions. We present QP-OneModel, a Unified Generative LLM for Multi-Task Query Understanding in the SNS domain. We reformulate heterogeneous sub-tasks into a unified sequence generation paradigm, adopting a progressive three-stage alignment strategy culminating in multi-reward Reinforcement Learning. Furthermore, QP-OneModel generates intent descriptions as a novel high-fidelity semantic signal, effectively augmenting downstream tasks such as query rewriting and ranking. Offline evaluations show QP-OneModel achieves a 7.35% overall gain over discriminative baselines, with significant F1 boosts in NER (+9.01%) and Term Weighting (+9.31%). It also exhibits superior generalization, surpassing a 32B model by 7.60% accuracy on unseen tasks. Fully deployed at Xiaohongshu, online A/B tests confirm its industrial value, optimizing retrieval relevance (DCG) by 0.21% and lifting user retention by 0.044%.