Optimizing search quality in SAP workflows by fine-tuning the Teuken-7B German LLM to generate structured JSON outputs from unstructured product descriptions.
Industrial ERP systems (like SAP) suffer from "dirty data." Product descriptions are inconsistent (e.g., "Screw M12" vs "M12 Screw Steel"). Standard search algorithms fail to match these duplicates. We needed a way to normalize this text into a strict Schema, but standard LLMs hallucinated non-existent fields.
Hover over the chart to see how the model's loss decreased (learning) while the JSON schema accuracy rose to near-perfection.