# Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation

**Published:** October 1, 2026
**Author:** Baode Wang, Zuming Huang, Kexuan Ren, Jun Huang, Wei Chu
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/improving-ocr-faithfulness-via-gated-and-attenuated-on-policy-distillati

Vision-language models may rewrite anomalous text in images into linguistically plausible expressions, compromising OCR transcription faithfulness. Sequence-level task rewards and local teacher guidance are complementary, but guidance from the same teacher may not remain equally…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2609.38282)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*