SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation
Summary: SciTables introduces a scalable, semi-automatically aligned benchmark of complex, math- and symbol-rich scientific tables paired with paper descriptions. Its reasoning-aware evaluation exposes failures in aggregation and factual grounding that semantic-similarity metrics and current generators miss. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Mehrnoush Alizade (Missouri University of Science and Technology)
- 2. Tengrui Kong (Missouri University of Science and Technology)
- 3. Suman Kalyan Maity (Missouri University of Science and Technology)
BibTeX Citation
@article{alizade_vldb26,
title = {{SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation}},
author = {Alizade, Mehrnoush and Kong, Tengrui and Maity, Suman Kalyan},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {3400--3412},
doi = {10.14778/3836663.3836697},
url = {https://doi.org/10.14778/3836663.3836697},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,620 | AutoDDG: Automated Dataset Description Generation using Large Language Models | 2026 | SIGMOD |
| 2 | 10,165 | Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding | 2025 | VLDB |
| 3 | 7,928 | TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations | 2025 | VLDB |
| 4 | 13,656 | Accelerating Tabular Inference: Training Data Generation with TENET | 2025 | VLDB |
| 5 | 5,687 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |
| 6 | 11,529 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 7 | 1,866 | ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems | 2024 | VLDB |
| 8 | 7,554 | Table Extraction and Understanding for Scientific and Enterprise Applications | 2020 | VLDB |
| 9 | 9,109 | Generation of Training Examples for Tabular Natural Language Inference | 2023 | SIGMOD |
| 10 | 1,978 | Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks | 2024 | SIGMOD |