mlsanityData to 7 Oct 2026

Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing

arXiv 2509.04469 ↗First posted 29 Aug 2025cs.CL cs.AIcited by 1

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

Abstract (arXiv)

This paper benchmarks eight multi-modal large language models from three families (GPT-5, Gemini 2.5, and open-source Gemma 3) on three diverse openly available invoice document datasets using zero-shot prompting. We compare two processing strategies: direct image processing using multi-modal capabilities and a structured parsing approach converting documents to markdown first. Results show native image processing generally outperforms structured approaches, with performance varying across model types and document characteristics. This benchmark provides insights for selecting appropriate models and processing strategies for automated document systems. Our code is available online.

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 16 of its 23 references that are in the map. First posted on arXiv 29 Aug 2025.

Builds on

16 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion14 Mar

Other references · 15

  1. 2025Gemma 3 Technical Reportcited by 1,686
  2. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
  3. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  4. 2021OCR-free Document Understanding Transformercited by 400
  5. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizationscited by 174
  6. 2022LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understandingcited by 107
  7. 2024DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systemscited by 37
  8. 2024M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Frameworkcited by 36
  9. 2020A Survey of Deep Learning Approaches for OCR and Document Understandingcited by 32
  10. 2024Docling Technical Reportcited by 29
  11. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  12. 2024WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Taskscited by 11
3 more
  1. 2021Field Extraction from Forms with Unlabeled Datacited by 4
  2. 2025Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliancecited by 4
  3. 2024Memory-Augmented Agent Training for Business Document Understandingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document QAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM
  2. 2025DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
  3. 2026Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction
  4. 2025Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark
  5. 2025Can Multi-modal (reasoning) LLMs detect document manipulation?
  6. 2024DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
  7. 2024A Review of Multi-Modal Large Language and Vision Models
  8. 2024Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters