dorsal/arxiv
View SchemaLEAPS: An LLM-Empowered Adaptive Plugin for Taobao AI Search
| Authors | Lei Wang, Jinhang Wu, Zhibin Wang, Biye Li, Haiping Hou |
|---|---|
| Categories | |
| ArXiv ID | 2601.05513vv1 |
| URL | https://arxiv.org/abs/2601.05513 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
The rapid advancement of large language models has reshaped user search cognition, driving a paradigm shift from discrete keyword-based search to high-dimensional conversational interaction. However, existing e-commerce search architectures face a critical capability deficit in adapting to this change. Users are often caught in a dilemma: precise natural language descriptions frequently trigger zero-result scenarios, while the forced simplification of queries leads to decision overload from noisy, generic results. To tackle this challenge, we propose LEAPS (LLM-Empowered Adaptive Plugin for Taobao AI Search), which seamlessly upgrades traditional search systems via a "Broaden-and-Refine" paradigm. Specifically, it attaches plugins to both ends of the search pipeline: (1) Upstream, a Query Expander acts as an intent translator. It employs a novel three-stage training strategy--inverse data augmentation, posterior-knowledge supervised fine-tuning, and diversity-aware reinforcement learning--to generate adaptive and complementary query combinations that maximize the candidate product set. (2) Downstream, a Relevance Verifier serves as a semantic gatekeeper. By synthesizing multi-source data (e.g., OCR text, reviews) and leveraging chain-of-thought reasoning, it precisely filters noise to resolve selection overload. Extensive offline experiments and online A/B testing demonstrate that LEAPS significantly enhances conversational search experiences. Crucially, its non-invasive architecture preserves established retrieval performance optimized for short-text queries, while simultaneously allowing for low-cost integration into diverse back-ends. Fully deployed on Taobao AI Search since August 2025, LEAPS currently serves hundreds of millions of users monthly.
{
"annotation_id": "0e762df2-c54b-4290-98ff-0a6ca0bfe4a1",
"date_created": "2026-02-17T05:53:04.442000Z",
"date_modified": "2026-02-17T05:53:04.442000Z",
"file_hash": "4635ea778463beb2cce8e52fb0950d88bb75ce90127d460afee5d62b5094bc99",
"private": false,
"record": {
"abstract": "The rapid advancement of large language models has reshaped user search cognition, driving a paradigm shift from discrete keyword-based search to high-dimensional conversational interaction. However, existing e-commerce search architectures face a critical capability deficit in adapting to this change. Users are often caught in a dilemma: precise natural language descriptions frequently trigger zero-result scenarios, while the forced simplification of queries leads to decision overload from noisy, generic results. To tackle this challenge, we propose LEAPS (LLM-Empowered Adaptive Plugin for Taobao AI Search), which seamlessly upgrades traditional search systems via a \"Broaden-and-Refine\" paradigm. Specifically, it attaches plugins to both ends of the search pipeline: (1) Upstream, a Query Expander acts as an intent translator. It employs a novel three-stage training strategy--inverse data augmentation, posterior-knowledge supervised fine-tuning, and diversity-aware reinforcement learning--to generate adaptive and complementary query combinations that maximize the candidate product set. (2) Downstream, a Relevance Verifier serves as a semantic gatekeeper. By synthesizing multi-source data (e.g., OCR text, reviews) and leveraging chain-of-thought reasoning, it precisely filters noise to resolve selection overload. Extensive offline experiments and online A/B testing demonstrate that LEAPS significantly enhances conversational search experiences. Crucially, its non-invasive architecture preserves established retrieval performance optimized for short-text queries, while simultaneously allowing for low-cost integration into diverse back-ends. Fully deployed on Taobao AI Search since August 2025, LEAPS currently serves hundreds of millions of users monthly.",
"arxiv_id": "2601.05513",
"authors": [
"Lei Wang",
"Jinhang Wu",
"Zhibin Wang",
"Biye Li",
"Haiping Hou"
],
"categories": [
"cs.IR"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "LEAPS: An LLM-Empowered Adaptive Plugin for Taobao AI Search",
"url": "https://arxiv.org/abs/2601.05513",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "d6f01a21-6e7a-405c-af58-501e4d6b723d",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}