QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs

TL;DR

This paper introduces a novel query-focused multi-table summarization method using a large language model, a new dataset, and demonstrates its effectiveness in generating tailored summaries for complex table data.

Contribution

It presents a new approach combining table serialization, a summarization controller, and LLMs, along with a comprehensive dataset for query-focused multi-table summarization.

Findings

The proposed method outperforms baseline approaches.

The dataset contains 4909 query-summary pairs with multiple tables.

Insights into challenges of complex table reasoning for accurate summarization.

Abstract

Table summarization is a crucial task aimed at condensing information from tabular data into concise and comprehensible textual summaries. However, existing approaches often fall short of adequately meeting users' information and quality requirements and tend to overlook the complexities of real-world queries. In this paper, we propose a novel method to address these limitations by introducing query-focused multi-table summarization. Our approach, which comprises a table serialization module, a summarization controller, and a large language model (LLM), utilizes textual queries and multiple tables to generate query-dependent table summaries tailored to users' information needs. To facilitate research in this area, we present a comprehensive dataset specifically tailored for this task, consisting of 4909 query-summary pairs, each associated with multiple tables. Through extensive experiments using our curated dataset, we demonstrate the effectiveness of our proposed method compared to baseline approaches. Our findings offer insights into the challenges of complex table reasoning for precise summarization, contributing to the advancement of research in query-focused multi-table summarization.