🧪 Test?View on arXiv
Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation
Not provided in the content
OCRdistillationreinforcement learningmultimodal
2609.38282
Builder Relevance
1h ago80%
Abstract
The paper introduces GAD-RL, a method that adaptively regulates teacher supervision during post-training to improve OCR transcription faithfulness.
Reality Card
Core Claim
GAD-RL achieves a Micro Recall of 59.92% on CHAOS-Bench, surpassing previous methods by significant margins.
Method / Result
Achieved 59.92% Micro Recall on CHAOS-Bench, surpassing GRPO and GRPO+OPD by 8.45 and 4.43 percentage points, respectively.
Limitations
The paper does not specify the authors or provide detailed experimental setups, which may hinder reproducibility.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.