QP-OneModel: 一个用于小红书搜索多任务查询理解的统一生成式大语言模型
QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search
AI总结：
QP-OneModel通过统一生成式大语言模型提升小红书搜索多任务查询理解的效率与准确性。
摘要：
查询处理（QP）在大规模社交网络服务（SNS）搜索引擎中架起了用户意图与内容供应之间的桥梁。传统QP系统依赖于隔离的判别模型（例如BERT）的管道，导致语义理解有限且维护成本高。虽然大语言模型（LLMs）提供了一个潜在的解决方案，但现有方法往往孤立地优化子任务，忽略了内在语义协同效应，并需要独立迭代。此外，标准生成方法通常缺乏对SNS场景的 grounding，无法弥合开放领域语料库与非正式SNS语言模式之间的差距，同时难以遵循严格的商业定义。我们提出了QP-OneModel，这是一个用于SNS领域多任务查询理解的统一生成式大语言模型。我们将异构子任务重新公式化为统一的序列生成范式，采用一种渐进的三阶段对齐策略，最终通过多奖励强化学习。此外，QP-OneModel生成意图描述作为新的高保真语义信号，有效增强了查询重写和排序等下游任务。离线评估显示，QP-OneModel在判别基线上的总体提升达到7.35%，在命名实体识别（NER）（+9.01%）和术语加权（+9.31%）方面有显著的F1提升。它还表现出优越的泛化能力，在未见过的任务上超越了32B模型，准确率提高了7.60%。完全部署在小红书上，在线A/B测试确认了其工业价值，优化检索相关性（DCG）0.21%并提升了用户留存0.044%。
英文摘要：
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%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
