SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911579380908032 |
|---|---|
| author | Gondhalekar, Chinmay Patel, Urjitkumar Yeh, Fang-Chun |
| author_facet | Gondhalekar, Chinmay Patel, Urjitkumar Yeh, Fang-Chun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04292 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats Gondhalekar, Chinmay Patel, Urjitkumar Yeh, Fang-Chun Computation and Language 68T50, 68T20 (Primary) 68T07, 68U15 (Secondary) I.2.7; I.2.8; H.3.3; H.3.1; I.5.4 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. |
| title | SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats |
| topic | Computation and Language 68T50, 68T20 (Primary) 68T07, 68U15 (Secondary) I.2.7; I.2.8; H.3.3; H.3.1; I.5.4 |
| url | https://arxiv.org/abs/2512.04292 |