When VLMs Trust Context: Evaluating Scene Text Recognition under Misleading Context

arXiv:2609.34781 · cs.CV, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/pasterinjlu/Context_OCR

Terminology

• Accuracy — 25× in this paper · explained in 1 episode
• Benchmark — 20× in this paper · explained in 2 episodes
• Scene Text Recognition — 8× in this paper
• Trace — 7× in this paper · explained in 2 episodes
• GRPO — 5× in this paper · explained in 6 episodes
• Hallucination — 5× in this paper · explained in 3 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 3× in this paper
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Generative Model — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• PaddleOCR 3.0 Technical Report
• Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions
• Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
• HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
• Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR
• MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
• When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR
• DeepSeek-OCR 2: Visual Causal Flow

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models