GIDCL: A Graph-Enhanced Interpretable Data Cleaning Framework with Large Language Models
Summary: GIDCL applies Graph Neural Networks on graphified tables to exploit structural correlations for data cleaning. A creator-critic workflow with LLMs yields interpretable cleaning rules and minimal labeled-data features, achieving ~10% F1 with 20 tuples. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Mengyi Yan (Beihang University)
- 2. Yaoshu Wang (Shenzhen University)
- 3. Yue Wang (Shenzhen University)
- 4. Xiaoye Miao (Zhejiang University)
- 5. Jianxin Li (Beihang University)
BibTeX Citation
@inproceedings{yan_sigmod24,
title = {{GIDCL: A Graph-Enhanced Interpretable Data Cleaning Framework with Large Language Models}},
author = {Yan, Mengyi and Wang, Yaoshu and Wang, Yue and Miao, Xiaoye and Li, Jianxin},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3698811},
url = {https://dl.acm.org/doi/10.1145/3698811},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,506 | This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch! | 2026 | SIGMOD | 5.093636e-05 |
| 10,882 | CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 43 of 43 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 | 7,894 | A Grammar-based Entity Representation Framework for Data Cleaning | 2009 | SIGMOD |
| 2 | 6,545 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |
| 3 | 7,880 | Learning Over Dirty Data Without Cleaning | 2020 | SIGMOD |
| 4 | 714 | Guided Data Repair | 2011 | VLDB |
| 5 | 10,572 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 6 | 5,518 | Self-supervised and Interpretable Data Cleaning with Sequence Generative Adversarial Networks | 2023 | VLDB |
| 7 | 10,431 | AutoDDG: Automated Dataset Description Generation using Large Language Models | 2026 | SIGMOD |
| 8 | 10,318 | In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration | 2026 | SIGMOD |
| 9 | 201 | Declarative Data Cleaning: Language, Model, and Algorithms | 2001 | VLDB |
| 10 | 5,682 | RetClean: Retrieval-Based Data Cleaning Using LLMs and Data Lakes | 2024 | VLDB |