Arctic-Extract Technical Report
Not on the map. Why?
Abstract (arXiv)
Arctic-Extract is a state-of-the-art model designed for extracting structural data (question answering, entities and tables) from scanned or digital-born business documents. Despite its SoTA capabilities, the model is deployable on resource-constrained hardware, weighting only 6.6 GiB, making it suitable for deployment on devices with limited resources, such as A10 GPUs with 24 GB of memory. Arctic-Extract can process up to 125 A4 pages on those GPUs, making suitable for long document processing. This paper highlights Arctic-Extract's training protocols and evaluation results, demonstrating its strong performance in document understanding.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 29 references that are in the map. First posted on arXiv 20 Nov 2025.
Builds on
13 of 29 references.
References · 13
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
- 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
- 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
- 2021Florence: A New Foundation Model for Computer Visioncited by 804
- 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
- 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 355
- 2023Document Understanding Dataset and Evaluation (DUDE)cited by 135
- 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
- 2021GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrievalcited by 39
- 2019Automatic Spanish Translation of the SQuAD Dataset for Multilingual Question Answeringcited by 35
1 more
Built on by
Not cited yet.