Skip to content

This repository compares output of LLM structural OCR using different prompting and chaining techniques

License

Notifications You must be signed in to change notification settings

gilinachum/LLM-OCR-Evaluation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Revisiting Structure OCR with multi-modal LLMs - detecting and resolving hallucinations

As Large Language Models (LLMs) evolve to process multiple modalities, we face challenges reminiscent of early text-based LLMs: basic inconsistency, inaccuracy, and hallucinations.

This example notebook demonstrates techniques to increase the accuracy of vision use cases using various techniques. Inlucded is a quick introduction to AWS Gen AI services landscape and how to get started with using Anthropic Claude and other LLMs on Amazon Bedrock.

About

This repository compares output of LLM structural OCR using different prompting and chaining techniques

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published