Mine and Refine: Optimizing Graded Relevance in E-commerce Semantic Search Retrieval

The paper introduces Mine and Refine, a two‑stage contrastive training framework designed to improve embedding‑based retrieval for large‑scale e‑commerce search. It tackles graded relevance, hard‑sample mining, and unstable similarity separability by using a lightweight LLM as a scalable labeler and a multi‑level circle loss to enforce margin‑controlled separation across relevance levels. The method has been deployed in production across multiple product verticals, yielding statistically significant increases in user engagement, gross order value, and retrieval relevance metrics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• rag
• fine-tuning