通过检索增强生成和多目标对齐统一查询自动补全中的排序与生成
Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment
AI总结：
提出一个统一框架，通过检索增强生成（RAG）和多目标直接偏好优化（DPO）将查询自动补全重构为端到端列表生成，解决传统流水线长尾覆盖不足和生成方法幻觉风险的问题，并在大规模商业搜索平台上验证了有效性。
摘要：
查询自动补全（QAC）在用户输入时建议查询补全，帮助用户表达意图并更高效地获取结果。现有方法面临根本性挑战：传统的检索-排序流水线长尾覆盖有限且需要大量特征工程，而最近的生成方法存在幻觉和安全风险。我们提出了一个统一框架，通过检索增强生成（RAG）和多目标直接偏好优化（DPO）将QAC重构为端到端列表生成。我们的方法结合了三个关键创新：（1）将QAC重构为具有多目标优化的端到端列表生成；（2）定义并部署一套基于规则、基于模型和以LLM为评判的验证器用于QAC，并在综合方法中使用它们，结合RAG、多目标DPO和迭代批评-修订以生成高质量合成数据；（3）一种混合服务架构，可在严格的延迟约束下实现高效的生产部署。在大规模商业搜索平台上的评估显示了显著改进：离线指标在所有维度上均有提升，人工评估获得+0.40至+0.69的偏好分数，受控在线实验实现了击键次数减少5.44%和建议采纳率增加3.46%，验证了结合RAG和多目标对齐的统一生成为生产级QAC提供了有效解决方案。这项工作代表了向由大语言模型、RAG和多目标对齐驱动的端到端生成的范式转变，建立了一个经过生产验证的框架，可惠及更广泛的搜索和推荐行业。
英文摘要：
Query Auto-Completion (QAC) suggests query completions as users type, helping them articulate intent and reach results more efficiently. Existing approaches face fundamental challenges: traditional retrieve-and-rank pipelines have limited long-tail coverage and require extensive feature engineering, while recent generative methods suffer from hallucination and safety risks. We present a unified framework that reformulates QAC as end-to-end list generation through Retrieval-Augmented Generation (RAG) and multi-objective Direct Preference Optimization (DPO). Our approach combines three key innovations: (1) reformulating QAC as end-to-end list generation with multi-objective optimization; (2) defining and deploying a suite of rule-based, model-based, and LLM-as-judge verifiers for QAC, and using them in a comprehensive methodology that combines RAG, multi-objective DPO, and iterative critique-revision for high-quality synthetic data; (3) a hybrid serving architecture enabling efficient production deployment under strict latency constraints. Evaluation on a large-scale commercial search platform demonstrates substantial improvements: offline metrics show gains across all dimensions, human evaluation yields +0.40 to +0.69 preference scores, and a controlled online experiment achieves 5.44\% reduction in keystrokes and 3.46\% increase in suggestion adoption, validating that unified generation with RAG and multi-objective alignment provides an effective solution for production QAC. This work represents a paradigm shift to end-to-end generation powered by large language models, RAG, and multi-objective alignment, establishing a production-validated framework that can benefit the broader search and recommendation industry.
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。
