MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables
This addresses a gap in table-based reasoning for users needing comprehensive insights from multiple tables, though it is incremental as it builds on existing retrieval-augmented generation approaches.
The paper tackles the problem of generating insights from multiple unknown tables, where existing methods are limited to single tables, by proposing MT-RAIG Bench as a benchmark and MT-RAIG Eval as an evaluation framework that better aligns with human judgments.
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.