DenTab: A Dataset for Table Recognition and Visual QA on Real-World Dental Estimates

TL;DR

DenTab is a new dataset with 2,000 real-world dental estimate tables designed to evaluate table recognition and visual question answering, highlighting current models' limitations and proposing a deterministic arithmetic reasoning pipeline.

Contribution

Introduces DenTab, a challenging dataset for table recognition and visual QA in noisy real-world settings, and proposes the Table Router Pipeline for reliable arithmetic reasoning.

Findings

Strong structure recovery does not ensure accurate multi-step reasoning.

Models struggle with arithmetic and consistency questions even with ground-truth tables.

The Table Router Pipeline improves arithmetic reliability without additional training.

Abstract

Tables condense key transactional and administrative information into compact layouts, but practical extraction requires more than text recognition: systems must also recover structure (rows, columns, merged cells, headers) and interpret roles such as line items, subtotals, and totals under common capture artifacts. Many existing resources for table structure recognition and TableVQA are built from clean digital-born sources or rendered tables, and therefore only partially reflect noisy administrative conditions. We introduce DenTab, a dataset of 2{,}000 cropped table images from dental estimates with high-quality HTML annotations, enabling evaluation of table recognition (TR) and table visual question answering (TableVQA) on the same inputs. DenTab includes 2{,}208 questions across eleven categories spanning retrieval, aggregation, and logic/consistency checks. We benchmark 16 systems, including 14 vision--language models (VLMs) and two OCR baselines. Across models, strong structure recovery does not consistently translate into reliable performance on multi-step arithmetic and consistency questions, and these reasoning failures persist even when using ground-truth HTML table inputs. To improve arithmetic reliability without training, we propose the Table Router Pipeline, which routes arithmetic questions to deterministic execution. The pipeline combines (i) a VLM that produces a baseline answer, a structured table representation, and a constrained table program with (ii) a rule-based executor that performs exact computation over the parsed table. The source code and dataset will be made publicly available at https://github.com/hamdilaziz/DenTab.