Large Language Models for Relevance Judgment in Product Search

TL;DR

This paper explores how large language models can be fine-tuned and optimized to automate relevance judgments in product search, achieving results comparable to human evaluators and improving search quality.

Contribution

It introduces novel techniques for fine-tuning billion-parameter LLMs with LoRA and various prompting strategies for relevance prediction in product search.

Findings

LLMs can be effectively fine-tuned for relevance judgment

Optimized LLMs outperform previous models and off-the-shelf solutions

Relevance predictions approach human evaluator quality

Abstract

High relevance of retrieved and re-ranked items to the search query is the cornerstone of successful product search, yet measuring relevance of items to queries is one of the most challenging tasks in product information retrieval, and quality of product search is highly influenced by the precision and scale of available relevance-labelled data. In this paper, we present an array of techniques for leveraging Large Language Models (LLMs) for automating the relevance judgment of query-item pairs (QIPs) at scale. Using a unique dataset of multi-million QIPs, annotated by human evaluators, we test and optimize hyper parameters for finetuning billion-parameter LLMs with and without Low Rank Adaption (LoRA), as well as various modes of item attribute concatenation and prompting in LLM finetuning, and consider trade offs in item attribute inclusion for quality of relevance predictions. We demonstrate considerable improvement over baselines of prior generations of LLMs, as well as off-the-shelf models, towards relevance annotations on par with the human relevance evaluators. Our findings have immediate implications for the growing field of relevance judgment automation in product search.