Captioning Visualizations with Large Language Models (CVLLM): A Tutorial
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929402596556800 |
|---|---|
| author | Carenini, Giuseppe Johnson, Jordon Salamatian, Ali |
| author_facet | Carenini, Giuseppe Johnson, Jordon Salamatian, Ali |
| contents | Automatically captioning visualizations is not new, but recent advances in large language models(LLMs) open exciting new possibilities. In this tutorial, after providing a brief review of Information Visualization (InfoVis) principles and past work in captioning, we introduce neural models and the transformer architecture used in generic LLMs. We then discuss their recent applications in InfoVis, with a focus on captioning. Additionally, we explore promising future directions in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19512 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Captioning Visualizations with Large Language Models (CVLLM): A Tutorial Carenini, Giuseppe Johnson, Jordon Salamatian, Ali Computation and Language Artificial Intelligence Human-Computer Interaction Automatically captioning visualizations is not new, but recent advances in large language models(LLMs) open exciting new possibilities. In this tutorial, after providing a brief review of Information Visualization (InfoVis) principles and past work in captioning, we introduce neural models and the transformer architecture used in generic LLMs. We then discuss their recent applications in InfoVis, with a focus on captioning. Additionally, we explore promising future directions in this field. |
| title | Captioning Visualizations with Large Language Models (CVLLM): A Tutorial |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2406.19512 |