AIBullisharXiv – CS AI · 9h ago6/10
🧠
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
Researchers introduce Consensus Entropy (CE), a training-free metric that improves OCR quality by measuring agreement across multiple Vision-Language Models, achieving 42.1% F1 score improvements over existing methods. The technique enables self-verifying OCR without supervision, addressing a critical gap in automated error detection for data generation pipelines used in LLM training.