VITA-MLLM/Woodpecker

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models

30
/ 100
Emerging

When working with AI models that describe images using text, sometimes those descriptions contain inaccuracies or 'hallucinations' that don't match the actual image content. This project helps identify and correct those errors. You provide an image and the AI-generated text description, and it returns a revised, more accurate text description. It's for anyone using or developing Multimodal Large Language Models (MLLMs) who needs to ensure their AI's visual descriptions are factually correct.

650 stars. No commits in the last 6 months.

Use this if you need to improve the reliability and factual accuracy of text generated by AI models that describe images.

Not ideal if you're looking for a tool to train a new multimodal AI model from scratch, as this focuses on post-generation correction.

AI-model-evaluation content-moderation image-captioning AI-safety natural-language-generation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

650

Forks

30

Language

Python

License

Last pushed

Dec 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/VITA-MLLM/Woodpecker"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.