TabSD: Large Free-Form Table Question Answering with SQL-Based Table Decomposition

2025-02-19

AI Summary

To address the limited understanding and reasoning capabilities of large language models (LLMs) in large-scale, schema-less, noisy free-form TableQA, this paper proposes an SQL-driven dynamic table decomposition framework. It leverages SQL generation to guide fine-grained subtable partitioning, integrates an SQL validator for structural consistency verification, and synergistically combines LLM-based semantic comprehension with programmatic structural constraints. We further introduce SLQA/SEQA—the first pure large-scale free-form TableQA benchmark—designed to rigorously evaluate robustness and generalization in unstructured tabular settings. Extensive experiments demonstrate that our method achieves absolute accuracy improvements of 23.07%, 2.84%, 23.24%, and 9.32% over the strongest baselines across four benchmarks, significantly enhancing noise robustness, interpretability, and cross-table generalization.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Question answering on free-form tables (TableQA) is challenging due to the absence of predefined schemas and the presence of noise in large tables. While Large Language Models (LLMs) have shown promise in TableQA, they struggle with large free-form tables and noise sensitivity. To address these challenges, we propose TabSD, a SQL-based decomposition model that enhances LLMs' ability to process large free-form tables. TabSD generates SQL queries to guide the table decomposition, remove noise, and processes sub-tables for better answer generation. Additionally, SQL Verifier refines SQL outputs to enhance decomposition accuracy. We introduce two TableQA datasets with large free-form tables, SLQA and SEQA, which consist solely of large free-form tables and will be publicly available. Experimental results on four benchmark datasets demonstrate that TABSD outperforms the best-existing baseline models by 23.07%, 2.84%, 23.24% and 9.32% in accuracy, respectively, highlighting its effectiveness in handling large and noisy free-form tables.

Problem

• Enhances LLMs' table processing
• Reduces noise in free-form tables
• Improves accuracy in TableQA

Innovation

• SQL-based table decomposition model
• SQL Verifier enhances accuracy
• Handles large noisy free-form tables