MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables

TL;DR

This paper introduces MT-RAIG Bench, a new benchmark and evaluation framework for assessing systems that generate insights by reasoning over multiple tables, addressing limitations of previous single-table approaches.

Contribution

It presents a novel benchmark and a fine-grained evaluation framework for multi-table insight generation, advancing beyond existing single-table reasoning methods.

Findings

Current LLMs struggle with complex multi-table reasoning

MT-RAIG Bench provides a challenging testbed for future research

The evaluation framework aligns better with human judgments

Abstract

Recent advancements in table-based reasoning have expanded beyond factoid-level QA to address insight-level tasks, where systems should synthesize implicit knowledge in the table to provide explainable analyses. Although effective, existing studies remain confined to scenarios where a single gold table is given alongside the user query, failing to address cases where users seek comprehensive insights from multiple unknown tables. To bridge these gaps, we propose MT-RAIG Bench, design to evaluate systems on Retrieval-Augmented Insight Generation over Mulitple-Tables. Additionally, to tackle the suboptimality of existing automatic evaluation methods in the table domain, we further introduce a fine-grained evaluation framework MT-RAIG Eval, which achieves better alignment with human quality judgments on the generated insights. We conduct extensive experiments and reveal that even frontier LLMs still struggle with complex multi-table reasoning, establishing our MT-RAIG Bench as a challenging testbed for future research.