Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2512.03025 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908750054424576 |
|---|---|
| author | Lu, Chenji Chen, Zhuo Zhao, Hui Zeng, Zhiyuan Zhao, Gang Ren, Junjie Xu, Ruicong Li, Haoran Liu, Songyan Wang, Pengjie Xu, Jian Zheng, Bo |
| author_facet | Lu, Chenji Chen, Zhuo Zhao, Hui Zeng, Zhiyuan Zhao, Gang Ren, Junjie Xu, Ruicong Li, Haoran Liu, Songyan Wang, Pengjie Xu, Jian Zheng, Bo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03025 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LORE: A Large Generative Model for Search Relevance Lu, Chenji Chen, Zhuo Zhao, Hui Zeng, Zhiyuan Zhao, Gang Ren, Junjie Xu, Ruicong Li, Haoran Liu, Songyan Wang, Pengjie Xu, Jian Zheng, Bo Information Retrieval Artificial Intelligence Computation and Language Machine Learning 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. |
| title | LORE: A Large Generative Model for Search Relevance |
| topic | Information Retrieval Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2512.03025 |