AutoDDG: Automated Dataset Description Generation using Large Language Models
Summary: AutoDDG generates dataset descriptions for tabular data by combining data-driven content summarization with LLM-based semantic enrichment, targeting missing/inaccurate metadata in data lakes/open portals. Proposes a multi-faceted evaluation (retrieval, reference-based, reference-free, human) and shows improved dataset search/retrieval at scale. (summarized by gpt-5-mini on Apr 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Haoxiang Zhang (New York University)
- 2. Yurong Liu (New York University)
- 3. Aécio Santos (New York University)
- 4. Wei-Lun (Allen) Hung (New York University)
- 5. Juliana Freire (New York University)
BibTeX Citation
@inproceedings{zhang_sigmod26,
title = {{AutoDDG: Automated Dataset Description Generation using Large Language Models}},
author = {Zhang, Haoxiang and Liu, Yurong and Santos, Aécio and Hung, Wei-Lun (Allen) and Freire, Juliana},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786626},
url = {https://dl.acm.org/doi/10.1145/3786626},
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 12 of 12 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 | 5,125 | Data-Driven Domain Discovery for Structured Datasets | 2020 | VLDB |
| 2 | 10,572 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 3 | 11,590 | Automated Relational Data Explanation using External Semantic Knowledge | 2022 | VLDB |
| 4 | 13,303 | Demonstrating CatDB: LLM-based Generation of Data-centric ML Pipelines | 2025 | SIGMOD |
| 5 | 10,882 | CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines | 2025 | VLDB |
| 6 | 9,155 | Adda: Towards Efficient in-Database Feature Generation via LLM-based Agents | 2025 | SIGMOD |
| 7 | 10,614 | LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning | 2026 | VLDB |
| 8 | 8,140 | Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study | 2024 | SIGMOD |
| 9 | 10,627 | Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution | 2026 | VLDB |
| 10 | 11,186 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |