# Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance

Source: [Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance](<https://www.sota2.com/research/paper/68fa7c301e209131cea8ced7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-26T05:03:02.866Z

Authors: Xixi Wang, Miguel Costa, Jordanka Kovaceva, Shuai Wang, Francisco C. Pereira

Published: 2025-06-04T20:21:52.000Z

## Abstract

Large language models (LLMs) have shown promise in table Question Answering (Table QA). However, extending these capabilities to multi-table QA remains challenging due to unreliable schema linking across complex tables. Existing methods based on semantic similarity work well only on simplified hand-crafted datasets and struggle to handle complex, real-world scenarios with numerous and diverse columns. To address this, we propose a graph-based framework that leverages human-curated relational knowledge to explicitly encode schema links and join paths. Given a natural language query, our method searches on graph to construct interpretable reasoning chains, aided by pruning and sub-path merging strategies to enhance efficiency and coherence. Experiments on both standard benchmarks and a realistic, large-scale dataset demonstrate the effectiveness of our approach. To our knowledge, this is the first multi-table QA system applied to truly complex industrial tabular data.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.04427>)

[PDF](<https://arxiv.org/pdf/2506.04427.pdf>)
