mlsanityData to 7 Oct 2026

Context-Independent OCR with Multimodal LLMs: Effects of Image Resolution and Visual Complexity

arXiv 2503.23667 ↗First posted 31 Mar 2025cs.CVcited by 2

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

Abstract (arXiv)

Due to their high versatility in tasks such as image captioning, document analysis, and automated content generation, multimodal Large Language Models (LLMs) have attracted significant attention across various industrial fields. In particular, they have been shown to surpass specialized models in Optical Character Recognition (OCR). Nevertheless, their performance under different image conditions remains insufficiently investigated, and individual character recognition is not guaranteed due to their reliance on contextual cues. In this work, we examine a context-independent OCR task using single-character images with diverse visual complexities to determine the conditions for accurate recognition. Our findings reveal that multimodal LLMs can match conventional OCR methods at about 300 ppi, yet their performance deteriorates significantly below 150 ppi. Additionally, we observe a very weak correlation between visual complexity and misrecognitions, whereas a conventional OCR-specific model exhibits no correlation. These results suggest that image resolution and visual complexity may play an important role in the reliable application of multimodal LLMs to OCR tasks that require precise character-level accuracy.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 8 of its 10 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

8 of 10 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning31 Dec
  2. 2024TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document7 Mar
  3. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models13 May

Other references · 5

  1. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 610
  2. 2023VTimeLLM: Empower LLM to Grasp Video Momentscited by 253
  3. 2023BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questionscited by 125
  4. 2023LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generationcited by 92
  5. 2023Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluationcited by 46

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanitiescited by 5
  2. 2026TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstructioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study
  2. 2025MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
  3. 2025Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
  4. 2025PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language
  5. 2024TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models
  6. 2026OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios
  7. 2026Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
  8. 2025E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition