Absolutely right - we tried estimating LLM confidence and the results are not great. Any process that requires reliability will struggle with LLM OCR.

https://news.ycombinator.com/item?id=43350816

LLMs are quite poor at rating their own confidence. Your best bet is to train a task specific LLM and ensure it is not overfit

We benchmarked it here - https://news.ycombinator.com/item?id=43350816