Report
Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models
| العنوان: | Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models |
|---|---|
| المؤلفون: | Scius-Bertrand, Anna, Jungo, Michael, Vögtlin, Lars, Spat, Jean-Marc, Fischer, Andreas |
| المصدر: | International Conference on Pattern Recognition - ICPR 2024, pp 152-166. Cham: Springer Nature Switzerland |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to near-perfect performance when considering hundreds of thousands of training samples. With the advent of large language models (LLMs), which are excellent few-shot learners, the question arises to what extent the document classification problem can be addressed with only a few training samples, or even none at all. In this paper, we investigate this question in the context of zero-shot prompting and few-shot model fine-tuning, with the aim of reducing the need for human-annotated training samples as much as possible. Comment: ICPR 2024 |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1007/978-3-031-78495-8_10 |
| URL الوصول: | http://arxiv.org/abs/2412.13859 |
| رقم الانضمام: | edsarx.2412.13859 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1007/978-3-031-78495-8_10 |
|---|