How well do LLMs reason over tabular data, really?

Published in 4th Table Representation Workshop - ACL 2025, 2025

This paper critically examines the reasoning capabilities of large language models when working with tabular data. We provide a comprehensive analysis of current limitations and propose methods for improving LLM performance on structured data reasoning tasks.

Recommended citation: Wolff, C., & Hulsebos, M. (2025). "How well do LLMs reason over tabular data, really?" 4th Table Representation Workshop - ACL 2025.