发表机构
Expedia Group（亿客行集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
度假租赁市场供应端失衡，长尾房源难获有效服务。本文提出无需训练的大语言模型候选生成管道，用静态房产元数据补充IBKNN，经联合融合等策略提升效果，扩大候选覆盖范围，缩小模型召回差距，有效服务长尾房源。
AI 中文摘要
度假租赁市场在供应端面临结构失衡：少数房产获得大部分用户互动，而新的、小众的和季节性房源的长尾产生的行为信号太少，协作过滤无法有效服务。在Vrbo，基于项目的k近邻（IBKNN）是核心候选生成渠道，但导致数万个房产没有候选，且为互动稀疏的房产生成的邻域较弱。我们提出了一个无需训练的基于大语言模型的候选生成管道，仅使用静态房产元数据来补充IBKNN。现成的大语言模型为每个房产合成不同的语义查询，预训练的文本编码器对其进行嵌入，近似最近邻索引从1170万个房产目录中检索候选。联合融合策略将这些与IBKNN合并，同时保留行为渠道的排序，保证对服务良好的房产不会降级，下游的排序学习模型对融合池重新评分。在160万个重点房产上进行评估，该系统将候选覆盖范围扩展到IBKNN无法触及的数万个房产，在行为方法最薄弱的长尾部分取得最大收益，在共享房产上的每个K值都能匹配或超过IBKNN。下游的排序学习阶段进一步提升融合池，产生一个完整的候选生成和重新排序堆栈，服务长尾而不使服务良好的房产退化。我们还表明，联合融合将3B开放权重的大语言模型与基于前沿API的模型之间的召回差距从27%-46%缩小到1%以下，支持在市场目录规模上进行自托管小模型部署。
英文摘要
Vacation rental marketplaces face a structural imbalance on the supply side: a small fraction of properties receive most user interactions, while the long tail of new, niche, and seasonal listings generates too little behavioral signal for collaborative filtering to serve effectively. At Vrbo, item-based k-nearest neighbors (IBKNN) is a core candidate generation channel, but leaves tens of thousands of properties with no candidates and produces weak neighborhoods for sparsely interacted ones. We present a training-free, LLM-based candidate generation pipeline that complements IBKNN using static property metadata alone. An off-the-shelf LLM synthesizes diverse semantic queries per property, a pre-trained text encoder embeds them, and an approximate nearest-neighbor index retrieves candidates from an 11.7M-property catalog. A Union fusion strategy merges these with IBKNN while preserving the behavioral channel's ordering, guaranteeing no degradation on well-served properties, and a downstream learning-to-rank model re-scores the fused pool. Evaluated on 1.6M focal properties, the system extends candidate coverage to tens of thousands of properties IBKNN cannot reach, delivers its largest gains on the long-tail segment where behavioral methods are weakest, and matches or beats IBKNN at every K on shared properties. A downstream learning-to-rank stage further lifts the fused pool, yielding a complete candidate generation and re-ranking stack that serves the long tail without regressing well-served properties. We additionally show that Union fusion collapses the recall gap between a 3B open-weights LLM and frontier API-based models from 27-46% to under 1%, supporting self-hosted small-model deployment at marketplace catalog scale.
CommentsAccepted at TSMO 2026 workshop, co-located with KDD 2026; 9 pages
