[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85743-en":3,"doc-seo-85743-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85743,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Serving the Long Tail: Training-Free LLM Candidate Generation for Vacation Rental Marketplaces","Vacation rental marketplaces suffer a supply-side imbalance where a small set of listings drives most interactions, leaving the long tail of new, niche, and seasonal items with insufficient behavioral signal for collaborative filtering. Vrbo’s item-based k-nearest neighbors (IBKNN) candidate generation leaves tens of thousands without candidates and forms weak neighborhoods. A training-free LLM pipeline synthesizes semantic queries from static metadata, embeds them, and retrieves candidates from an 11.7M catalog. Union fusion preserves IBKNN ordering and a learning-to-rank stage re-scores the fused pool, expanding coverage on long-tail properties without harming well-served items.","Serving the Long Tail: Training-Free LLM Candidate Generation  \nfor Vacation Rental Marketplaces  \nSyed Mohammed Arshad Zaidi  \n[syzaidi@expediagroup.com](syzaidi@expediagroup.com)[ ](syzaidi@expediagroup.com)Expedia Group Austin, Texas, USA  \nEric Rincon  \n[erincon@expediagroup.com](erincon@expediagroup.com)[ ](erincon@expediagroup.com)Expedia Group Austin, Texas, USA  \nShayan Hassantabar  \n[shassantabar@expediagroup.com](shassantabar@expediagroup.com)[ ](shassantabar@expediagroup.com)Expedia Group Austin, Texas, USA  \narXiv :2607 .09877v 1 [ cs .LG] 10 Jul 2026  \nAbstract  \nVacation 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 􀀠 on shared properties. A downstream learning-to-rank stage further lifts the fused pool, yielding a complete candidate generation andre-ranking stack that serves the long tail without regressing wellserved properties. We additionally show that Union fusion collapses the recall gap between a 3B open-weights LLM and frontier APIbased models from 27–46% to under 1%, supporting self-hosted small-model deployment at marketplace catalog scale.  \nCCS Concepts  \n• Information systems → Recommender systems; • Computing methodologies → Learning to rank; Natural language generation.  \nKeywords  \ncandidate generation, large language models, dense retrieval, coldstart, long-tail recommendation, two-sided marketplaces, vacation rentals, learning to rank  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference acronym ’XX, Woodstock, NY  \n© 2018 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nACM Reference Format:  \nSyed Mohammed Arshad Zaidi, Eric Rincon, and Shayan Hassantabar. 2018. Serving the Long Tail: Training-Free LLM Candidate Generation for Vacation Rental Marketplaces. In Proceedings of Make sure to enter the correct conference title from your rights confirmation email (Conference acronym ’XX) . ACM, New York, NY, USA, 9 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \n1 Introduction  \nVacation rental marketplaces like Vr","cbCaif04y1ZUtwYV","https://ap.wps.com/l/cbCaif04y1ZUtwYV","pdf",571775,1,9,"English","en",105,"# Introduction\n## Marketplace recommendation and the candidate generation bottleneck\n## IBKNN limitations on the long tail\n# Training-free LLM candidate generation pipeline","[{\"question\":\"Why does candidate generation struggle for vacation rental marketplaces’ long-tail listings?\",\"answer\":\"Because new, niche, and seasonal properties have little or no co-occurrence data, so collaborative-filtering signals become unavailable or noisy, limiting which candidates can be generated.\"},{\"question\":\"How does the training-free LLM candidate generation pipeline work?\",\"answer\":\"An off-the-shelf LLM uses static property metadata to synthesize diverse semantic queries per property, a pre-trained text encoder embeds them, and an approximate nearest-neighbor index retrieves candidates from the full catalog.\"},{\"question\":\"What is the role of Union fusion and learning-to-rank in the proposed approach?\",\"answer\":\"Union fusion merges LLM-retrieved candidates with IBKNN candidates while preserving IBKNN’s ordering and avoiding degradation on well-served properties; a downstream learning-to-rank model then re-scores the fused pool to improve effectiveness.\"}]",1784205972,23,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"serving-the-long-tail-training-free-llm-candidate-generation-for-vacation-rental-marketplaces","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/serving-the-long-tail-training-free-llm-candidate-generation-for-vacation-rental-marketplaces/85743/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does candidate generation struggle for vacation rental marketplaces’ long-tail listings?","Question",{"text":75,"@type":76},"Because new, niche, and seasonal properties have little or no co-occurrence data, so collaborative-filtering signals become unavailable or noisy, limiting which candidates can be generated.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the training-free LLM candidate generation pipeline work?",{"text":80,"@type":76},"An off-the-shelf LLM uses static property metadata to synthesize diverse semantic queries per property, a pre-trained text encoder embeds them, and an approximate nearest-neighbor index retrieves candidates from the full catalog.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of Union fusion and learning-to-rank in the proposed approach?",{"text":84,"@type":76},"Union fusion merges LLM-retrieved candidates with IBKNN candidates while preserving IBKNN’s ordering and avoiding degradation on well-served properties; a downstream learning-to-rank model then re-scores the fused pool to improve effectiveness.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]