Papers for

catalog data engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Task conditioning improves defect detection across large product catalogs

Positional task conditioning for scalable defect detection across product families in large product catalogs

Abstract: Product families in large product catalogs suffer from inconsistencies such as duplicates and unit mismatches that degrade customer experience. Detecting these requires reasoning over multiple error types across lengthy product listings, where LLM classification quality degrades due to long-context limitations. We address this by decomposing detection into focused sub-tasks that reduce context and isolate error types, improving F1 from 52\% to 87\%. For scalable deployment, we introduce Positional Task Conditioning (PTC), which distills this capability into a single smaller model by reinforcing task identity at structural prompt boundaries. PTC outperforms rationale-based distillation across five models and two architecture families, achieving within 1.79\% F1 of the frontier at upto 98\% lower cost. Our system is deployed across multiple countries processing 10+ million product families.

Wed 9 SeptMachine Learning

The gist

Large product catalogs often have problems like duplicated items or mismatched units, which can confuse buyers. The authors show that breaking down these problems into smaller, focused tasks helps computers find errors much better. They create a new method called Positional Task Conditioning that lets a smaller, efficient computer model handle many tasks at once while keeping detection accuracy high. This system is already used in multiple countries to check millions of product families.

Open → 2609.09567v1