mlsanityData to 14 Oct 2026

Notes on Applicability of GPT-4 to Document Understanding

arXiv 2405.18433 ↗First posted 28 May 2024cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

We perform a missing, reproducible evaluation of all publicly available GPT-4 family models concerning the Document Understanding field, where it is frequently required to comprehend text spacial arrangement and visual clues in addition to textual semantics. Benchmark results indicate that though it is hard to achieve satisfactory results with text-only models, GPT-4 Vision Turbo performs well when one provides both text recognized by an external OCR engine and document images on the input. Evaluation is followed by analyses that suggest possible contamination of textual GPT-4 models and indicate the significant performance drop for lengthy documents.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

10 of 20 references.

References · 10

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  3. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  4. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  5. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 179
  6. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 135
  7. 2024InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructionscited by 27
  8. 2024GRAM: Global Reasoning for Multi-Page VQAcited by 23
  9. 2020Document Visual Question Answering Challenge 2020cited by 20
  10. 2020From Dataset Recycling to Multi-Property Extraction and Beyondcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 3.

7 papers.

  1. 2024Improve Vision Language Model Chain-of-thought Reasoningcited by 136
  2. 2024Large Language Models for Page Stream Segmentationcited by 5
  3. 2025The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formattingcited by 5
  4. 2024Arctic-TILT. Business Document Understanding at Sub-Billion Scalecited by 3
  5. 2025Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysiscited by 2
  6. 2024Hespi: A pipeline for automatically detecting information from hebarium specimen sheetscited by 1
  7. 2025Unchecked and Overlooked: Addressing the Checkbox Blind Spot in Large Language Models with CheckboxQAcited by 1