In this paper, we investigate the effectiveness of various LLMs in interpreting tabular data through different prompting strategies and data formats. Our analyses extend across six benchmarks for table-related tasks such as question-answering and fact-checking. We introduce for the first time the assessment of LLMs' performance on image-based table representations. Specifically, we compare five text-based and three image-based table representations, demonstrating the role of representation and prompting on LLM performance. Our study provides insights into the effective use of LLMs on table-related tasks.
@article{arxiv.2402.12424,
title = {Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs},
author = {Naihao Deng and Zhenjie Sun and Ruiqi He and Aman Sikka and Yulong Chen and Lin Ma and Yue Zhang and Rada Mihalcea},
journal= {arXiv preprint arXiv:2402.12424},
year = {2024}
}
Comments
Accepted to ACL 2024 Findings; Naihao and Zhenjie contributed equally to the project; Data available at: https://github.com/dnaihao/Tables-as-Texts-or-Images