FormaT5: Abstention and Examples for Conditional Table Formatting with Natural Language
Summary: FormaT5 generates spreadsheet conditional-formatting rules from tables and natural-language intent. Its distinctive abstention objective predicts underspecified arguments as placeholders, resolved by a second model or programming-by-example, outperforming eight neural baselines on a 1,053-task benchmark. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Mukul Singh (Microsoft)
- 2. José Cambronero (Microsoft)
- 3. Sumit Gulwani (Microsoft)
- 4. Vu Le (Microsoft)
- 5. Carina Negreanu (Microsoft)
- 6. Elnaz Nouri (Microsoft)
- 7. Mohammad Raza (Microsoft)
- 8. Gust Verbruggen (Microsoft)
BibTeX Citation
@article{singh_vldb24,
title = {{FormaT5: Abstention and Examples for Conditional Table Formatting with Natural Language}},
author = {Singh, Mukul and Cambronero, José and Gulwani, Sumit and Le, Vu and Negreanu, Carina and Nouri, Elnaz and Raza, Mohammad and Verbruggen, Gust},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {3},
pages = {497--510},
doi = {10.14778/3632093.3632111},
url = {https://doi.org/10.14778/3632093.3632111},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,192 | PLM4NDV: Minimizing Data Access for Number of Distinct Values Estimation with Pre-trained Language Models | 2025 | SIGMOD | 4.9793485e-05 |
| 11,343 | CoLA: Model Collaboration for Log-based Anomaly Detection | 2025 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 329 | Can Foundation Models Wrangle Your Data? | 2023 | VLDB | 0.00020858443 |
| 439 | ATHENA: An Ontology-Driven System for Natural Language Querying over Relational Data Stores | 2016 | VLDB | 0.00018251249 |
| 536 | NaLIR: An Interactive Natural Language Interface for Querying Relational Databases | 2014 | SIGMOD | 0.00016771934 |
| 1,211 | Query From Examples: An Iterative, Data-Driven Approach to Query Construction | 2015 | VLDB | 0.00011524858 |
| 11,757 | Cornet: Learning Table Formatting Rules By Example | 2023 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,109 | Generation of Training Examples for Tabular Natural Language Inference | 2023 | SIGMOD |
| 2 | 4,424 | Auto-Transform: Learning-to-Transform by Patterns | 2020 | VLDB |
| 3 | 13,584 | SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation | 2026 | VLDB |
| 4 | 8,266 | Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study | 2024 | SIGMOD |
| 5 | 4,630 | Transformers for Tabular Data Representation: A Tutorial on Models and Applications | 2022 | VLDB |
| 6 | 7,928 | TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations | 2025 | VLDB |
| 7 | 1,978 | Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks | 2024 | SIGMOD |
| 8 | 13,712 | Cornet: Learning Spreadsheet Formatting Rules By Example | 2023 | VLDB |
| 9 | 7,812 | Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations | 2024 | SIGMOD |
| 10 | 11,757 | Cornet: Learning Table Formatting Rules By Example | 2023 | VLDB |