Scaling and Stabilizing Large-Scale Embedding-Based Retrieval

Jul 14, 2026

Researchers at Walmart present a unified pipeline for embedding-based retrieval that addresses both training-inference gaps and challenges in model evolution. Their approach combines hybrid hard negative mining and legacy-aware distillation, enabling a smooth transition to higher-capacity models. The system, deployed in live production, achieved a +7.34% improvement in NDCG@5 and a +0.50% increase in gross revenue.

Why it matters: This work demonstrates practical advances for improving the effectiveness and stability of large-scale embedding-based retrieval systems in real-world e-commerce settings.

Full story at: arXiv Information Retrieval ↗