A Survey of Table Reasoning with Large Language Models

TL;DR

This survey reviews how large language models are transforming table reasoning, highlighting techniques, advantages, and future research directions to improve understanding and application of LLMs in this domain.

Contribution

It provides a comprehensive summary of existing LLM-based table reasoning methods, analyzing their techniques, benefits, and future research opportunities.

Findings

LLMs significantly outperform previous methods in table reasoning.

Existing research lacks a unified summary of LLM-based techniques.

Future directions include improving methods and expanding practical applications.

Abstract

Table reasoning, which aims to generate the corresponding answer to the question following the user requirement according to the provided table, and optionally a text description of the table, effectively improving the efficiency of obtaining information. Recently, using Large Language Models (LLMs) has become the mainstream method for table reasoning, because it not only significantly reduces the annotation cost but also exceeds the performance of previous methods. However, existing research still lacks a summary of LLM-based table reasoning works. Due to the existing lack of research, questions about which techniques can improve table reasoning performance in the era of LLMs, why LLMs excel at table reasoning, and how to enhance table reasoning abilities in the future, remain largely unexplored. This gap significantly limits progress in research. To answer the above questions and advance table reasoning research with LLMs, we present this survey to analyze existing research, inspiring future work. In this paper, we analyze the mainstream techniques used to improve table reasoning performance in the LLM era, and the advantages of LLMs compared to pre-LLMs for solving table reasoning. We provide research directions from both the improvement of existing methods and the expansion of practical applications to inspire future research.