mlsanityData to 7 Oct 2026

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

arXiv 2607.05614 ↗First posted 6 Jul 2026cs.CL cs.AI cs.CVcited by 0

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

Abstract (arXiv)

Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in real-world, human-centric applications. However, this adoption is limited for low-resource languages such as Bangla due to the scarcity of high-quality annotated data. To address this gap, we introduce BaFCo, a benchmark dataset for Bangla form comprehension with a focus on Document Layout Analysis (DLA) and Key Information Extraction (KIE). BaFCo curates 200 multi-page complex Bangladeshi government forms, sourced from across diverse sectors including agriculture, education, banking, and land management. To accurately capture the structural and contextual complexity of these forms, we define a fine-grained annotation schema comprising 26 types of form entities, along with a separate coarse form entity set consisting of 5 types. We evaluate the latest MLLMs from the ChatGPT, Gemini, Claude, Qwen, and Kimi series using zero-shot and chain-of-thought prompts under both low and high reasoning setups. Our results reveal limitations in current MLLMs' ability in comprehending Bangla forms, particularly in accurately localizing highly granular form entities. Our dataset and code is available at: https://huggingface.co/datasets/Mausul/bafco

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 29 of its 42 references that are in the map. First posted on arXiv 6 Jul 2026.

Builds on

29 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Docopilot: Improving Multimodal Models for Document-Level Understanding19 Jul
  2. 2024DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming27 Jun

Other references · 27

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  4. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 742
  5. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  6. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  7. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 345
  8. 2024mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understandingcited by 220
  9. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 152
  10. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 146
  11. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 144
  12. 2023DocLLM: A layout-aware generative language model for multimodal document understandingcited by 112
15 more
  1. 2022LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understandingcited by 107
  2. 2021BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documentscited by 104
  3. 2024The rising costs of training frontier AI modelscited by 91
  4. 2021Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layoutscited by 82
  5. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  6. 2024Understanding the Performance and Estimating the Cost of LLM Fine-Tuningcited by 48
  7. 2024LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understandingcited by 24
  8. 2024DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understandingcited by 23
  9. 2023Form-NLU: Dataset for the Form Natural Language Understandingcited by 14
  10. 2023BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Datasetcited by 13
  11. 2023GenKIE: Robust Generative Multimodal Document Key Information Extractioncited by 8
  12. 2024BuDDIE: A Business Document Dataset for Multi-task Information Extractioncited by 8
  13. 2025A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trendscited by 8
  14. 2022GMN: Generative Multi-modal Network for Practical Document Information Extractioncited by 6
  15. 2025Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challengescited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms
  2. 2025BnMMLU: Measuring Massive Multitask Language Understanding in Bengali
  3. 2024MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis
  4. 2025BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali
  5. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations
  6. 2024Needle In A Multimodal Haystack
  7. 2026MORE: A Multilingual Document Parsing Benchmark and Evaluation
  8. 2024SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension