Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs

Abstract

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.

arXiv commentAccepted to ACL 2024 Findings; Naihao and Zhenjie contributed equally to the project; Data available at: https://github.com/dnaihao/Tables-as-Texts-or-Images