Positional task conditioning for scalable defect detection across product families in large product catalogs
TL;DR
Positional Task Conditioning (PTC) is introduced, which distills this capability into a single smaller model by reinforcing task identity at structural prompt boundaries by outperforms rationale-based distillation across five models and two architecture families.
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.
