# Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs

arXiv: https://arxiv.org/abs/2510.23941 · HTML: https://mlsanity.com/paper/2510.23941/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [Large Language Models for Generative Recommendation: A Survey and Visionary Discussions](https://mlsanity.com/paper/2309.01157/) (2023)
- [PRewrite: Prompt Rewriting with Reinforcement Learning](https://mlsanity.com/paper/2401.08189/) (2024)
- [Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together](https://mlsanity.com/paper/2407.10930/) (2024)
- [Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs](https://mlsanity.com/paper/2305.09858/) (2023)
- [Using LLMs for the Extraction and Normalization of Product Attribute Values](https://mlsanity.com/paper/2403.02130/) (2024)
- [Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction](https://mlsanity.com/paper/2311.05922/) (2023)
- [ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback](https://mlsanity.com/paper/2407.00087/) (2024)
- [Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies](https://mlsanity.com/paper/2402.09282/) (2024)
- [Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data](https://mlsanity.com/paper/2006.08779/) (2020)
- [Learning variant product relationship and variation attributes from e-commerce website structures](https://mlsanity.com/paper/2410.02779/) (2024)
- [A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models](https://mlsanity.com/paper/2501.03508/) (2025)

## Built on by (most cited first, 4 of 4)

- [CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Models](https://mlsanity.com/paper/2607.14396/) (2026)
- [When Do LLMs Actually Help? Evaluating LLMs as Data Quality Annotators](https://mlsanity.com/paper/2608.18158/) (2026)
- [Retrieve, Match, Escalate: Accurate and Scalable Product Linking with VLM-Distilled Cross-Encoders and Agentic VLMs](https://mlsanity.com/paper/2608.25037/) (2026)
- [Positional task conditioning for scalable defect detection across product families in large product catalogs](https://mlsanity.com/paper/2609.09567/) (2026)

## Abstract (arXiv)

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.