English

Retrieve, Annotate, Evaluate, Repeat: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation

Information Retrieval 2024-09-19 v1 Artificial Intelligence Computation and Language Emerging Technologies Human-Computer Interaction

Abstract

Evaluating production-level retrieval systems at scale is a crucial yet challenging task due to the limited availability of a large pool of well-trained human annotators. Large Language Models (LLMs) have the potential to address this scaling issue and offer a viable alternative to humans for the bulk of annotation tasks. In this paper, we propose a framework for assessing the product search engines in a large-scale e-commerce setting, leveraging Multimodal LLMs for (i) generating tailored annotation guidelines for individual queries, and (ii) conducting the subsequent annotation task. Our method, validated through deployment on a large e-commerce platform, demonstrates comparable quality to human annotations, significantly reduces time and cost, facilitates rapid problem discovery, and provides an effective solution for production-level quality control at scale.

Keywords

Cite

@article{arxiv.2409.11860,
  title  = {Retrieve, Annotate, Evaluate, Repeat: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation},
  author = {Kasra Hosseini and Thomas Kober and Josip Krapac and Roland Vollgraf and Weiwei Cheng and Ana Peleteiro Ramallo},
  journal= {arXiv preprint arXiv:2409.11860},
  year   = {2024}
}

Comments

13 pages, 5 figures, 4 Tables

R2 v1 2026-06-28T18:48:50.401Z