Arctic-TILT. Business Document Understanding at Sub-Billion Scale

The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed on a single 24GB GPU, lowering operational costs w...

Full description

Saved in:
Bibliographic Details
Main Authors Borchmann, Łukasz, Pietruszka, Michał, Jaśkowski, Wojciech, Jurkiewicz, Dawid, Halama, Piotr, Józiak, Paweł, Garncarek, Łukasz, Liskowski, Paweł, Szyndler, Karolina, Gretkowski, Andrzej, Ołtusek, Julita, Nowakowska, Gabriela, Zawłocki, Artur, Duhr, Łukasz, Dyda, Paweł, Turski, Michał
Format Journal Article
LanguageEnglish
Published 08.08.2024
Subjects
Computer Science - Computation and Language
Computer Science - Computer Vision and Pattern Recognition
Online AccessGet full text

Cover

More Information
Summary:The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed on a single 24GB GPU, lowering operational costs while processing Visually Rich Documents with up to 400k tokens. The model establishes state-of-the-art results on seven diverse Document Understanding benchmarks, as well as provides reliable confidence scores and quick inference, which are essential for processing files in large-scale or time-sensitive enterprise environments.
DOI:10.48550/arxiv.2408.04632