发表机构
University of Science and Technology of China; Taobao & Tmall Group of Alibaba; Nankai University（中国科学技术大学; 阿里巴巴淘宝天猫集团; 南开大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对电商搜索召回与粗排整合问题，提出VARG生成式检索系统，通过RQ-VAE语义前缀、价值排序令牌及Prefix-GRPO对齐，在离线与在线测试中提升GMV、IPV和PCTR。
AI 中文摘要
在电商搜索中整合召回与粗排，要求候选生成在最终排序之前兼顾相关性、个性化和商业价值。为此，我们提出了VARG，一个用于天猫App搜索的生成式检索系统，该系统直接将生成的商品候选提交给现有的最终排序器。VARG-ID使用RQ-VAE构建语义前缀，通过双向查询-商品对比学习增强搜索相关性，并将这些前缀与按价值排序的第三令牌相结合，以提供细粒度的商品地址和商业价值先验。三阶段监督微调逐步学习商品到标识符的映射、查询语义检索和个性化检索。个性化模型训练将价值感知和层级对齐的监督与扩展的用户上下文相结合，并使用局部序数监督（LO-SFT）来学习由第三令牌编码的局部簇内排序。Prefix-GRPO结合了基于输出合法性、用户行为、排序器优势和搜索相关性的门控奖励，以及前缀感知的令牌加权，使候选生成与商业价值和排序目标对齐。协调的每日商品和模型更新在纳入新产品和行为反馈的同时保留现有商品地址。在数千万商品上的离线实验验证了标识符的稳定性，并展示了SFT策略和Prefix-GRPO相对于各自基线在检索质量和头部价值召回方面的提升。在一项覆盖20%搜索流量的14天在线A/B测试中，VARG直接将生成的候选提交给最终排序器，使GMV提升了1.45%，人均IPV提升了0.22%，PCTR提升了0.31%。在线购物导购查询评估进一步表明，VARG在较小的候选配额下保持了有竞争力的相关性。
英文摘要
Integrating recall and pre-ranking in e-commerce search requires candidate generation to account for relevance, personalization, and business value before final ranking. To this end, we present VARG, a generative retrieval system for Tmall App search that directly admits generated item candidates to the existing final ranker. VARG-ID constructs semantic prefixes using RQ-VAE, enhances search relevance through bidirectional query-item contrastive learning, and combines these prefixes with a value-ordered third token to provide fine-grained item addresses and a business-value prior. Three-stage supervised fine-tuning progressively learns item-to-identifier mappings, query-semantic retrieval, and personalized retrieval. Personalized model training combines value-aware and hierarchy-aligned supervision with expanded user context, and uses local ordinal supervision (LO-SFT) to learn the local within-cluster ordering encoded by the third token. Prefix-GRPO combines gated rewards based on output legality, user behavior, ranker advantage, and search relevance with prefix-aware token weighting to align candidate generation with business value and ranking objectives. Coordinated daily product and model updates preserve existing item addresses while incorporating new products and behavioral feedback. Offline experiments on tens of millions of products validate identifier stability and demonstrate gains in retrieval quality and head-level value recall from SFT strategies and Prefix-GRPO over their respective baselines. In a 14-day online A/B test covering 20% of search traffic, VARG directly admits generated candidates to the final ranker and improves GMV by 1.45%, per-user IPV by 0.22%, and PCTR by 0.31%. Online shopping-guide query evaluations further show that VARG maintains competitive relevance with a smaller candidate quota.
Comments11 pages, 4 figures, 7 tables
