Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks
Summary: Table-GPT introduces table fine-tuning for GPT-3.5/ChatGPT: continue-training on synthetic tasks distilled from real relational tables to improve 2D table understanding. Yields consistent gains on data transformation/cleaning/imputation/table-QA, including unseen holdout tasks, while preserving instruction-following generalization. (summarized by gpt-5.4-mini on May 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Peng Li (Georgia Institute of Technology)
- 2. Yeye He (Microsoft)
- 3. Dror Yashar (Microsoft)
- 4. Weiwei Cui (Microsoft)
- 5. Song Ge (Microsoft)
- 6. Haidong Zhang (Microsoft)
- 7. Danielle Rifinski Fainman (Microsoft)
- 8. Dongmei Zhang (Microsoft)
- 9. Surajit Chaudhuri (Microsoft)
BibTeX Citation
@inproceedings{li_sigmod24,
title = {{Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks}},
author = {Li, Peng and He, Yeye and Yashar, Dror and Cui, Weiwei and Ge, Song and Zhang, Haidong and Fainman, Danielle Rifinski and Zhang, Dongmei and Chaudhuri, Surajit},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3654979},
url = {https://dl.acm.org/doi/10.1145/3654979},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 20 of 20 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 27 of 27 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 7,482 | Table Extraction and Understanding for Scientific and Enterprise Applications | 2020 | VLDB |
| 2 | 11,186 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 3 | 9,067 | Making Table Understanding Work in Practice | 2022 | CIDR |
| 4 | 1,981 | ReAcTable: Enhancing ReAct for Table Question Answering | 2024 | VLDB |
| 5 | 2,790 | GitTables: A Large-Scale Corpus of Relational Tables | 2023 | SIGMOD |
| 6 | 11,050 | TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery | 2025 | VLDB |
| 7 | 8,140 | Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study | 2024 | SIGMOD |
| 8 | 8,945 | Generation of Training Examples for Tabular Natural Language Inference | 2023 | SIGMOD |
| 9 | 9,505 | TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations | 2025 | VLDB |
| 10 | 6,545 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |