Research

Paper

TESTING March 20, 2026

GenFacet: End-to-End Generative Faceted Search via Multi-Task Preference Alignment in E-Commerce

Authors

Zhouwei Zhai, Min Yang, Jin Li

Abstract

Faceted search acts as a critical bridge for navigating massive ecommerce catalogs, yet traditional systems rely on static rule-based extraction or statistical ranking, struggling with emerging vocabulary, semantic gaps, and a disconnect between facet selection and underlying retrieval. In this paper, we introduce GenFacet, an industrial-grade, end-to-end generative framework deployed at JD.com. GenFacet reframes faceted search as two coupled generative tasks within a unified Large Language Model: Context-Aware Facet Generation, which dynamically synthesizes trend-responsive navigation options, and Intent-Driven Query Rewriting, which translates user interactions into precise search queries to close the retrieval loop. To bridge the gap between generative capabilities and search utility, we propose a novel multi-task training pipeline combining teacher-student distillation with GRPO. This aligns the model with complex user preferences by directly optimizing for downstream search satisfaction. Validated on China's largest selfoperated e-commerce platform via rigorous offline evaluations and online A/B tests, GenFacet demonstrated substantial improvements. Specifically, online results reveal a relative increase of 42.0% in facet Click-Through Rate (CTR) and 2.0% in User Conversion Rate (UCVR). These outcomes provide strong evidence of the benefits of generative methods for improving query understanding and user engagement in large-scale information retrieval systems.

Metadata

arXiv ID: 2603.19665
Provider: ARXIV
Primary Category: cs.IR
Published: 2026-03-20
Fetched: 2026-03-23 16:54

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.19665v1</id>\n    <title>GenFacet: End-to-End Generative Faceted Search via Multi-Task Preference Alignment in E-Commerce</title>\n    <updated>2026-03-20T06:01:01Z</updated>\n    <link href='https://arxiv.org/abs/2603.19665v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.19665v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Faceted search acts as a critical bridge for navigating massive ecommerce catalogs, yet traditional systems rely on static rule-based extraction or statistical ranking, struggling with emerging vocabulary, semantic gaps, and a disconnect between facet selection and underlying retrieval. In this paper, we introduce GenFacet, an industrial-grade, end-to-end generative framework deployed at JD.com. GenFacet reframes faceted search as two coupled generative tasks within a unified Large Language Model: Context-Aware Facet Generation, which dynamically synthesizes trend-responsive navigation options, and Intent-Driven Query Rewriting, which translates user interactions into precise search queries to close the retrieval loop. To bridge the gap between generative capabilities and search utility, we propose a novel multi-task training pipeline combining teacher-student distillation with GRPO. This aligns the model with complex user preferences by directly optimizing for downstream search satisfaction. Validated on China's largest selfoperated e-commerce platform via rigorous offline evaluations and online A/B tests, GenFacet demonstrated substantial improvements. Specifically, online results reveal a relative increase of 42.0% in facet Click-Through Rate (CTR) and 2.0% in User Conversion Rate (UCVR). These outcomes provide strong evidence of the benefits of generative methods for improving query understanding and user engagement in large-scale information retrieval systems.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n    <published>2026-03-20T06:01:01Z</published>\n    <arxiv:primary_category term='cs.IR'/>\n    <author>\n      <name>Zhouwei Zhai</name>\n    </author>\n    <author>\n      <name>Min Yang</name>\n    </author>\n    <author>\n      <name>Jin Li</name>\n    </author>\n  </entry>"
}