QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines

Large language models (LLMs) have been widely used for relevance assessment in information retrieval.However, our study demonstrates that combining two distinct small language models (SLMs) with different architectures can outperform LLMs in this task.Our approach-QUPID-integrates a generative SLM with an embedding-based SLM, achieving more accurate relevance judgments while reducing computational costs compared to state-of-the-art LLM solutions.This computational efficiency makes QUPID highly scalable for real-world search systems processing hundreds of millions of queries daily.In experiments across diverse document types, our method demonstrated consistent performance improvements (Cohen's Kappa of 0.646 versus 0.387 for leading LLMs) while offering up to 60x faster inference.Furthermore, when integrated into production search pipelines, QUPID improved nDCG@5 scores by 1.9%.These findings underscore how architectural diversity in model combinations can significantly enhance both search relevance and operational efficiency in information retrieval systems.