# Vision Language Models for Spreadsheet Understanding: Challenges and Opportunities

arXiv: https://arxiv.org/abs/2405.16234 · HTML: https://mlsanity.com/paper/2405.16234/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 25 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [The E2E Dataset: New Challenges For End-to-End Generation](https://mlsanity.com/paper/1706.09254/) (2017)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [TUTA: Tree-based Transformers for Generally Structured Table Pre-training](https://mlsanity.com/paper/2010.12537/) (2020)
- [TableFormer: Table Structure Understanding with Transformers](https://mlsanity.com/paper/2203.01017/) (2022)
- [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023)
- [Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs](https://mlsanity.com/paper/2310.10358/) (2023)
- [Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks](https://mlsanity.com/paper/2201.09745/) (2022)
- [Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling](https://mlsanity.com/paper/2303.06949/) (2023)
- [Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs](https://mlsanity.com/paper/2402.12424/) (2024)
- [TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning](https://mlsanity.com/paper/2312.09039/) (2023)
- [An End-to-End Multi-Task Learning Model for Image-based Table Recognition](https://mlsanity.com/paper/2303.08648/) (2023)
- [Assessing GPT4-V on Structured Reasoning Tasks](https://mlsanity.com/paper/2312.11524/) (2023)
- [TableSense: Spreadsheet Table Detection with Convolutional Neural Networks](https://mlsanity.com/paper/2106.13500/) (2021)
- [The Future of Spreadsheets in the Big Data Era](https://mlsanity.com/paper/1801.10231/) (2018)

## Built on by (most cited first, 4 of 4)

- [Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows](https://mlsanity.com/paper/2512.13168/) (2025)
- [Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models](https://mlsanity.com/paper/2507.02978/) (2025)
- [Table Comprehension in Building Codes using Vision Language Models and Domain-Specific Fine-Tuning](https://mlsanity.com/paper/2511.18306/) (2025)
- [From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsing](https://mlsanity.com/paper/2608.09842/) (2026)

## Abstract (arXiv)

This paper explores capabilities of Vision Language Models on spreadsheet comprehension. We propose three self-supervised challenges with corresponding evaluation metrics to comprehensively evaluate VLMs on Optical Character Recognition (OCR), spatial perception, and visual format recognition. Additionally, we utilize the spreadsheet table detection task to assess the overall performance of VLMs by integrating these challenges. To probe VLMs more finely, we propose three spreadsheet-to-image settings: column width adjustment, style change, and address augmentation. We propose variants of prompts to address the above tasks in different settings. Notably, to leverage the strengths of VLMs in understanding text rather than two-dimensional positioning, we propose to decode cell values on the four boundaries of the table in spreadsheet boundary detection. Our findings reveal that VLMs demonstrate promising OCR capabilities but produce unsatisfactory results due to cell omission and misalignment, and they notably exhibit insufficient spatial and format recognition skills, motivating future work to enhance VLMs' spreadsheet data comprehension capabilities using our methods to generate extensive spreadsheet-image pairs in various settings.