LORE: A Large Generative Model for Search Relevance

TL;DR

LORE introduces a large generative model framework for e-commerce search relevance, achieving significant online performance improvements through a structured development process and capability decomposition.

Contribution

It presents a comprehensive blueprint for LLM-based relevance, including a novel training paradigm, a benchmark for evaluation, and deployment strategies tailored for online systems.

Findings

Achieved +27% improvement in online GoodRate metrics.

Developed the RAIR benchmark for core relevance capabilities.

Implemented a query frequency-stratified deployment strategy.

Abstract

Achievement. We introduce LORE, a systematic framework for Large Generative Model-based relevance in e-commerce search. Deployed and iterated over three years, LORE achieves a cumulative +27\% improvement in online GoodRate metrics. This report shares the valuable experience gained throughout its development lifecycle, spanning data, features, training, evaluation, and deployment. Insight. While existing works apply Chain-of-Thought (CoT) to enhance relevance, they often hit a performance ceiling. We argue this stems from treating relevance as a monolithic task, lacking principled deconstruction. Our key insight is that relevance comprises distinct capabilities: knowledge and reasoning, multi-modal matching, and rule adherence. We contend that a qualitative-driven decomposition is essential for breaking through current performance bottlenecks. Contributions. LORE provides a complete blueprint for the LLM relevance lifecycle. Key contributions include: (1) A two-stage training paradigm combining progressive CoT synthesis via SFT with human preference alignment via RL. (2) A comprehensive benchmark, RAIR, designed to evaluate these core capabilities. (3) A query frequency-stratified deployment strategy that efficiently transfers offline LLM capabilities to the online system. LORE serves as both a practical solution and a methodological reference for other vertical domains.