mlsanityData to 7 Oct 2026

Geometric Risk Control for Vision-Language Model OCR

arXiv 2603.19790 ↗First posted 20 Mar 2026cs.CVcited by 1

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

Abstract (arXiv)

Vision-language models (VLMs) enable flexible generative optical character recognition (OCR), while their open-ended decoders can expose wrong but fluent text with weak visual support. In audit-sensitive records, such an output can be more costly than abstention. Frozen or externally served VLMs therefore require an external decision layer that can determine whether a transcription has sufficient visual evidence for release. We introduce the Geometric Risk Controller (GRC), a model-agnostic controller that treats controlled geometric transformations as repeatable black-box probes, screens structurally implausible continuations, and releases the unique candidate supported by coherent cross-view evidence. The protocol provides empirical selective exposure control with explicit coverage and query cost under a reproducible fixed decision rule. Experiments across frozen VLMs and standard scene-text benchmarks consistently reduce mean, upper-tail, and catastrophic error among released outputs while retaining high coverage.

Key facts. Cited by 1 paper 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 21 of its 29 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

21 of 29 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Ocean-OCR: Towards General OCR Application via a Vision-Language Model26 Jan
  2. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models13 May

Other references · 19

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  3. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  4. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  5. 2017Selective Classification for Deep Neural Networkscited by 799
  6. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  7. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 468
  8. 2022Conformal Risk Controlcited by 290
  9. 2023Efficient Guided Generation for Large Language Modelscited by 192
  10. 2024LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Modelcited by 128
  11. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  12. 2024Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Modelscited by 46
7 more
  1. 2024Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoningcited by 37
  2. 2024TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Modelscited by 27
  3. 2025Efficient Test-Time Scaling for Small Vision-Language Modelscited by 11
  4. 2025SAFER: Risk-Constrained Sample-then-Filter in Large Language Modelscited by 7
  5. 2026Mechanisms of Prompt-Induced Hallucination in Vision-Language Modelscited by 4
  6. 2025MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMscited by 3
  7. 2025PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editionscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2025Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
  2. 2026Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
  3. 2026How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations
  4. 2026From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists
  5. 2025DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model
  6. 2025Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
  7. 2026Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models
  8. 2026LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR