AICLJun 4, 2025

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

arXiv:2506.04427v39 citationsh-index: 12EMNLP
Originality Incremental advance
AI Analysis

This addresses the problem of extending LLM capabilities to complex multi-table QA for industrial applications, representing an incremental improvement over existing methods.

The paper tackles the challenge of unreliable schema linking in multi-table question answering by proposing a graph-based framework that uses human-curated relational knowledge to encode schema links and join paths, achieving effectiveness on both standard benchmarks and a realistic large-scale industrial dataset.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes