Your model doesn't need to write the answer. It needs to point at it.

You gave the LLM the answer. So why is it writing it out from scratch? Send a model a support ticket and four labels, and ask which one fits. It writes back {"label": "billing"}, one token at a time. The word "billing" was in your prompt the whole time. Extraction is the same. The invoice number is in the PDF, and the model types it back to you.... Weiterlesen: Your model doesn't need to write the answer. It needs to point at it.