# Self-Play Fine-Tuning

SP-DocReader is a self-play framework for document OCR that aligns reference and generated readings with a longest common subsequence, applies contrastive relative scoring and direct negative log-likelihood supervision only at unmatched positions, and trains only the OCR module while the visual encoder and language backbone stay frozen; across Qwen3-VL-4B and InternVL-3.5-4B, three self-play rounds reduce Vary-600K character error rate relative to two-epoch supervised fine-tuning and improve DocBank, IIT-CDIP, DocVQA and InfographicVQA scores.

SP-DocReader is a self-play framework for document OCR that aligns reference and generated readings with a longest common subsequence, applies contrastive relative scoring and direct negative log-likelihood supervision only at unmatched positions, and trains only the OCR module while the visual encoder and language backbone stay frozen; across Qwen3-VL-4B and InternVL-3.5-4B, three self-play rounds reduce Vary-600K character error rate relative to two-epoch supervised fine-tuning and improve DocBank, IIT-CDIP, DocVQA and InfographicVQA scores.