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

arXiv: https://arxiv.org/abs/2506.04427 · HTML: https://mlsanity.com/paper/2506.04427/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [Qwen2.5-1M Technical Report](https://mlsanity.com/paper/2501.15383/) (2025)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios](https://mlsanity.com/paper/2403.19318/) (2024)
- [The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models](https://mlsanity.com/paper/2408.07702/) (2024)
- [OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment](https://mlsanity.com/paper/2502.14913/) (2025)
- [A Survey on Table Question Answering: Recent Advances](https://mlsanity.com/paper/2207.05270/) (2022)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering](https://mlsanity.com/paper/2305.12820/) (2023)
- [Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval](https://mlsanity.com/paper/2404.09889/) (2024)
- [Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering](https://mlsanity.com/paper/2402.11194/) (2024)
- [STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing](https://mlsanity.com/paper/2210.11888/) (2022)
- [Parameter-Efficient Abstractive Question Answering over Tables or Text](https://mlsanity.com/paper/2204.03357/) (2022)
- [iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering](https://mlsanity.com/paper/2506.01784/) (2025)

## Built on by (most cited first, 7 of 7)

- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment](https://mlsanity.com/paper/2605.19577/) (2026)
- [KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2603.21440/) (2026)
- [DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation](https://mlsanity.com/paper/2603.21430/) (2026)
- [Position: How can Graphs Help Large Language Models?](https://mlsanity.com/paper/2605.02452/) (2026)
- [LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study](https://mlsanity.com/paper/2603.21439/) (2026)
- [JoinGR: Learning to Traverse Join Graphs for Table Retrieval](https://mlsanity.com/paper/2610.01064/) (2026)

## Abstract (arXiv)

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.