Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback

Fatemeh Pesaran Zadeh, Juyeon Kim, Jin-Hwa Kim, Gunhee Kim


Abstract
Large language models (LLMs) have demonstrated strong capabilities across various language tasks, notably through instruction-tuning methods. However, LLMs face challenges in visualizing complex, real-world data through charts and plots. Firstly, existing datasets rarely cover a full range of chart types, such as 3D, volumetric, and gridded charts. Secondly, supervised fine-tuning methods do not fully leverage the intricate relationships within rich datasets, including text, code, and figures. To address these challenges, we propose a hierarchical pipeline and a new dataset for chart generation. Our dataset, Text2Chart31, includes 31 unique plot types referring to the Matplotlib library, with 11.1K tuples of descriptions, code, data tables, and plots. Moreover, we introduce a reinforcement learning-based instruction tuning technique for chart generation tasks without requiring human feedback. Our experiments show that this approach significantly enhances the model performance, enabling smaller models to outperform larger open-source models and be comparable to state-of-the-art proprietary models in data visualization tasks.
Anthology ID:
2024.emnlp-main.640
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11459–11480
Language:
URL:
https://aclanthology.org/2024.emnlp-main.640/
DOI:
10.18653/v1/2024.emnlp-main.640
Bibkey:
Cite (ACL):
Fatemeh Pesaran Zadeh, Juyeon Kim, Jin-Hwa Kim, and Gunhee Kim. 2024. Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 11459–11480, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback (Pesaran Zadeh et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.640.pdf
Software:
 2024.emnlp-main.640.software.zip