We introduce a novel, training free cascade for auto-prompting Large Language Models (LLMs) to assess product quality in e-commerce. Our system requires no training labels or model fine-tuning, instead automatically generating and refining prompts for evaluating attribute quality across tens of thousands of product category-attribute pairs. Starting from a seed of human-crafted prompts, the cascade progressively optimizes instructions to meet catalog-specific requirements. This approach bridges the gap between general language understanding and domain-specific knowledge at scale in complex industrial catalogs. Our extensive empirical evaluations shows the auto-prompt cascade improves precision and recall by 8−10% over traditional chain-of-thought prompting. Notably, it achieves these gains while reducing domain expert effort from 5.1 hours to 3 minutes per attribute - a 99% reduction. Additionally, the cascade generalizes effectively across five languages and multiple quality assessment tasks, consistently maintaining performance gains.
@article{arxiv.2510.23941,
title = {Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs},
author = {Soham Satyadharma and Fatemeh Sheikholeslami and Swati Kaul and Aziz Umit Batur and Suleiman A. Khan},
journal= {arXiv preprint arXiv:2510.23941},
year = {2025}
}