LEAPS: An LLM-Empowered Adaptive Plugin in Taobao AI Search

TL;DR

LEAPS is an adaptive plugin that enhances Taobao AI Search by expanding and refining user queries using large language models, significantly improving search relevance and user experience.

Contribution

The paper introduces LEAPS, a novel LLM-empowered plugin with a 'Broaden-and-Refine' paradigm, improving search accuracy and flexibility in e-commerce applications.

Findings

LEAPS improves search relevance and user satisfaction.

LEAPS maintains existing retrieval performance while adding new capabilities.

LEAPS has been deployed on Taobao serving hundreds of millions of users.

Abstract

The rapid rise of large language models has shifted user search behavior from discrete keywords to natural-language, multi-constraint queries--a shift existing e-commerce search architectures struggle to accommodate. Users face a dilemma: precise natural-language queries often trigger zero-result scenarios, while forced simplification yields noisy, generic results that overwhelm decision-making. To address this, we propose LEAPS (LLM-Empowered Adaptive Plugin in Taobao AI Search), which upgrades traditional search pipelines via a "Broaden-and-Refine" paradigm by attaching plugins at both ends. (1) Upstream, a Query Expander generates adaptive, complementary query combinations to maximize the candidate set, trained via a three-stage strategy of inverse data augmentation, posterior-knowledge supervised fine-tuning, and diversity-aware reinforcement learning. (2) Downstream, a Relevance Verifier filters noise by synthesizing multi-source signals (e.g., OCR text, reviews) with chain-of-thought reasoning. Extensive offline experiments and online A/B testing show that LEAPS significantly enhances the conversational shopping experience, while its non-intrusive architecture preserves established short-text retrieval performance and enables low-cost integration with diverse back-ends. Fully deployed on Taobao AI Search since August 2025, LEAPS serves hundreds of millions of users monthly.