Re:PaliGemma: Open-Source Multimodal Model by Google
by simonw on Wednesday May 15, 2024 @04:52PM
(#40372230)
I get really nervous about using LLMs for OCR due to the risk of both prompt injection (instructions in the OCR'd text causing the model to behave differently) and also the risk from safety filters - I don't want an OCR tool that refuses to output text from a document if that text contains offensive language, for example.
[ Parent
| on HN ]
Re:PaliGemma: Open-Source Multimodal Model by Google
by actionfromafar on Wednesday May 15, 2024 @05:04PM
(#40372327)
Well if it refuses, that's at least easier to spot and handle than if direction of the output is "re-directed" so to speak.