English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

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

Forum topic · 小凯 · 2026-07-05

Summary

This February 2025 arXiv paper (arXiv:2502.15990) by Jayant Sachdev, Sean D Rosario, Abhijeet Phatak, He Wen, Swati Kirti, and Chittaranjan Tripathy proposes an automated framework for labeling query-product relevance in e-commerce search using large language models. Relevance labeling is a critical yet costly bottleneck in building retrieval and ranking systems, since traditional approaches rely on manual annotation by human judges, which is slow, expensive, and inconsistent. The authors explore how LLMs can generate graded relevance judgments for query-product pairs, examining prompting strategies and alignment with human labels. The work shows that carefully prompted LLMs can achieve strong agreement with human annotators, making them viable for producing large-scale training data for retrieval and ranking models at a fraction of the cost of human labeling. The paper situates itself in the broader trend of applying LLMs to industrial search pipelines, where scaling high-quality supervision data is a key challenge. Readers should consult the original PDF for exact experimental numbers and methodology details. This summary is based on the paper's abstract and metadata as indexed on a Chinese tech forum.

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

Overview

  • Paper: Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search
  • Authors: Jayant Sachdev, Sean D Rosario, Abhijeet Phatak, He Wen, Swati Kirti, Chittaranjan Tripathy
  • Published: February 2025, arXiv
  • Link: https://arxiv.org/abs/2502.15990
  • Background and Motivation

    E-commerce search systems depend on large volumes of query-product relevance labels for training retrieval and ranking models. Traditionally, these labels are produced by human judges — a process that is slow, expensive, hard to scale, and prone to inconsistency across annotators. As product catalogs and query volumes grow, manual labeling becomes a serious bottleneck.

    This paper investigates whether large language models (LLMs) can automate this labeling process, generating graded relevance judgments for query-product pairs at scale while maintaining alignment with human judgment.

    Core Idea

    The authors propose using LLMs to assess the relevance of a product to a given shopping query, producing graded relevance labels that can be used to:

  • Train and fine-tune retrieval and ranking models
  • Augment or replace scarce human-annotated data
  • Enable rapid iteration when catalog content or query distributions change
  • Key considerations include prompt design for e-commerce relevance (understanding user intent, product attributes, and match quality) and calibrating LLM outputs against human-labeled benchmarks.

    Why It Matters

    1. Cost and scale: LLM labeling can reduce the cost of relevance annotation by orders of magnitude compared to human judges. 2. Consistency: Models apply criteria uniformly, avoiding drift between annotators. 3. Data flywheel: Better labels improve retrieval/ranking models, which improve search quality and downstream conversion.

    Takeaways for Search/Rec Practitioners

  • LLM-as-annotator pipelines are becoming a standard component of industrial search data infrastructure.
  • Agreement with human labels must be validated before replacing manual annotation wholesale; hybrid human-LLM labeling is a common compromise.
  • Offline label quality should still be cross-checked against online metrics (CTR, satisfaction), as label-level agreement does not guarantee end-to-end gains.
  • > Note: This post is based on the paper's abstract and public metadata. For exact experimental results, datasets, and methodology details, refer to the original paper on arXiv.

    Related Reading

  • Behavior Modeling Space Reconstruction for E-Commerce Search (arXiv:2501.18216)
  • Applying Deep Learning to Ads Conversion Prediction in Last Mile Delivery (arXiv:2502.10514)
  • Behavior-driven query similarity prediction based on pre-trained language models

Tags

#large-language-models#e-commerce-search#relevance-labeling#information-retrieval#learning-to-rank#data-annotation#arxiv#search-ranking

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178209040