Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search

TL;DR

This paper demonstrates that Large Language Models can automate query-product relevance labeling in e-commerce, achieving near-human accuracy more efficiently and at scale, thus improving search quality and reducing costs.

Contribution

The study applies prompt engineering techniques to LLMs for large-scale relevance labeling, showing their potential to replace traditional human annotation in e-commerce search.

Findings

LLMs can approach human-level accuracy in relevance labeling

Prompt engineering enhances LLM performance in this task

The approach reduces time and cost compared to human labeling

Abstract

Accurate query-product relevance labeling is indispensable to generate ground truth dataset for search ranking in e-commerce. Traditional approaches for annotating query-product pairs rely on human-based labeling services, which is expensive, time-consuming and prone to errors. In this work, we explore the application of Large Language Models (LLMs) to automate query-product relevance labeling for large-scale e-commerce search. We use several publicly available and proprietary LLMs for this task, and conducted experiments on two open-source datasets and an in-house e-commerce search dataset. Using prompt engineering techniques such as Chain-of-Thought (CoT) prompting, In-context Learning (ICL), and Retrieval Augmented Generation (RAG) with Maximum Marginal Relevance (MMR), we show that LLM's performance has the potential to approach human-level accuracy on this task in a fraction of the time and cost required by human-labelers, thereby suggesting that our approach is more efficient than the conventional methods. We have generated query-product relevance labels using LLMs at scale, and are using them for evaluating improvements to our search algorithms. Our work demonstrates the potential of LLMs to improve query-product relevance thus enhancing e-commerce search user experience. More importantly, this scalable alternative to human-annotation has significant implications for information retrieval domains including search and recommendation systems, where relevance scoring is crucial for optimizing the ranking of products and content to improve customer engagement and other conversion metrics.