@inproceedings{satyadharma-etal-2025-auto,
    title = "Auto prompting without training labels: An {LLM} cascade for product quality assessment in e-commerce catalogs",
    author = "Satyadharma, Soham  and
      Sheikholeslami, Fatemeh  and
      Kaul, Swati  and
      Batur, Aziz Umit  and
      Khan, Suleiman A.",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.emnlp-industry.63/",
    doi = "10.18653/v1/2025.emnlp-industry.63",
    pages = "937--953",
    ISBN = "979-8-89176-333-3",
    abstract = "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."
}