Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Satyadharma, Soham, Sheikholeslami, Fatemeh, Kaul, Swati, Batur, Aziz Umit, Khan, Suleiman A.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.23941
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911236388552704
author Satyadharma, Soham
Sheikholeslami, Fatemeh
Kaul, Swati
Batur, Aziz Umit
Khan, Suleiman A.
author_facet Satyadharma, Soham
Sheikholeslami, Fatemeh
Kaul, Swati
Batur, Aziz Umit
Khan, Suleiman A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23941
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs
Satyadharma, Soham
Sheikholeslami, Fatemeh
Kaul, Swati
Batur, Aziz Umit
Khan, Suleiman A.
Computation and Language
Artificial Intelligence
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.
title Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.23941