Re:Replace OCR with Vision Language Models
by fzysingularity on Thursday February 27, 2025 @12:08AM
(#43191546)
Yes, both false positives and false negatives like the one you mentioned happens when the schema is sometimes ill-defined. Making name optional via `name: str | None` actually turns out ensure that the model only fills it if it’s certain that field exists.
These are some of the nuances we had to work with during VLM fine-tuning with structured JSON.
These are some of the nuances we had to work with during VLM fine-tuning with structured JSON.