News for hackers. Stuff that matters.
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.

Re:Replace OCR with Vision Language Models by rafram on Thursday February 27, 2025 @07:48AM (#43193908)
You seem to be missing my point.