SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats

TL;DR

SQuARE is a hybrid retrieval system for tabular data that preserves structure and improves question answering accuracy over complex spreadsheets by intelligently routing queries.

Contribution

It introduces a complexity-aware routing framework that combines structure-preserving retrieval with SQL-based methods for robust table question answering.

Findings

Outperforms single-strategy baselines and ChatGPT-4o in accuracy.

Maintains header hierarchies, time labels, and units for faithful cell value retrieval.

Achieves consistent retrieval precision and answer accuracy across diverse datasets.

Abstract

Accurate question answering over real spreadsheets remains difficult due to multirow headers, merged cells, and unit annotations that disrupt naive chunking, while rigid SQL views fail on files lacking consistent schemas. We present SQuARE, a hybrid retrieval framework with sheet-level, complexity-aware routing. It computes a continuous score based on header depth and merge density, then routes queries either through structure-preserving chunk retrieval or SQL over an automatically constructed relational representation. A lightweight agent supervises retrieval, refinement, or combination of results across both paths when confidence is low. This design maintains header hierarchies, time labels, and units, ensuring that returned values are faithful to the original cells and straightforward to verify. Evaluated on multi-header corporate balance sheets, a heavily merged World Bank workbook, and diverse public datasets, SQuARE consistently surpasses single-strategy baselines and ChatGPT-4o on both retrieval precision and end-to-end answer accuracy while keeping latency predictable. By decoupling retrieval from model choice, the system is compatible with emerging tabular foundation models and offers a practical bridge toward a more robust table understanding.