# Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR

arXiv: https://arxiv.org/abs/2601.03714 · HTML: https://mlsanity.com/paper/2601.03714/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [DocLLM: A layout-aware generative language model for multimodal document understanding](https://mlsanity.com/paper/2401.00908/) (2023)
- [Focus Anywhere for Fine-grained Multi-page Document Understanding](https://mlsanity.com/paper/2405.14295/) (2024)
- [Disentangling visual and written concepts in CLIP](https://mlsanity.com/paper/2206.07835/) (2022)
- [Probing Visual Language Priors in VLMs](https://mlsanity.com/paper/2501.00569/) (2024)

## Built on by (most cited first, 8 of 8)

- [Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding](https://mlsanity.com/paper/2602.01785/) (2026)
- [Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions](https://mlsanity.com/paper/2605.27750/) (2026)
- [Decoupling semantics from vision: A framework for faithful visual-text compression evaluation](https://mlsanity.com/paper/2608.01848/) (2026)
- [How to Utilize Complementary Vision-Text Information for 2D Structure Understanding](https://mlsanity.com/paper/2603.16245/) (2026)
- [Using OCR Heads to Verbalize Image Semantics](https://mlsanity.com/paper/2609.18823/) (2026)
- [When VLMs Trust Context: Evaluating Scene Text Recognition under Misleading Context](https://mlsanity.com/paper/2609.34781/) (2026)
- [TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering](https://mlsanity.com/paper/2610.19551/) (2026)
- [Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR](https://mlsanity.com/paper/2610.20461/) (2026)

## Abstract (arXiv)

DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. While this suggests a promising solution for the LLM long-context bottleneck, we investigate a critical question: "Visual merit or linguistic crutch - which drives DeepSeek-OCR's performance?" By employing sentence-level and word-level semantic corruption, we isolate the model's intrinsic OCR capabilities from its language priors. Results demonstrate that without linguistic support, DeepSeek-OCR's performance plummets from approximately 90% to 20%. Comparative benchmarking against 13 baseline models reveals that traditional pipeline OCR methods exhibit significantly higher robustness to such semantic perturbations than end-to-end methods. Furthermore, we find that lower visual token counts correlate with increased reliance on priors, exacerbating hallucination risks. Context stress testing also reveals a total model collapse around 10,000 text tokens, suggesting that current optical compression techniques may paradoxically aggravate the long-context bottleneck. This study empirically defines DeepSeek-OCR's capability boundaries and offers essential insights for future optimizations of the vision-text compression paradigm. We release all data, results and scripts used in this study at https://github.com/dududuck00/DeepSeekOCR.