AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
This provides a publicly available resource to accelerate development of models for Arabic structured data, addressing a gap due to limited resources and unique language features, though it is incremental as it adapts existing benchmark approaches to a new language.
The authors tackled the lack of benchmarks for evaluating large language models (LLMs) on Arabic tabular data by creating AraTable, a comprehensive benchmark with tasks like question answering and fact verification. Initial analyses show LLMs perform adequately on simple tasks but face significant challenges on complex reasoning, with the proposed automated evaluation framework achieving performance nearly identical to human judges.
The cognitive and reasoning abilities of large language models (LLMs) have enabled remarkable progress in natural language processing. However, their performance in interpreting structured data, especially in tabular formats, remains limited. Although benchmarks for English tabular data are widely available, Arabic is still underrepresented because of the limited availability of public resources and its unique language features. To address this gap, we present AraTable, a novel and comprehensive benchmark designed to evaluate the reasoning and understanding capabilities of LLMs when applied to Arabic tabular data. AraTable consists of various evaluation tasks, such as direct question answering, fact verification, and complex reasoning, involving a wide range of Arabic tabular sources. Our methodology follows a hybrid pipeline, where initial content is generated by LLMs and subsequently filtered and verified by human experts to ensure high dataset quality. Initial analyses using AraTable show that, while LLMs perform adequately on simpler tabular tasks such as direct question answering, they continue to face significant cognitive challenges when tasks require deeper reasoning and fact verification. This indicates that there are substantial opportunities for future work to improve performance on complex tabular reasoning tasks. We also propose a fully automated evaluation framework that uses a self-deliberation mechanism and achieves performance nearly identical to that of human judges. This research provides a valuable, publicly available resource and evaluation framework that can help accelerate the development of foundational models for processing and analysing Arabic structured data.