Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution
Summary: KATS constructs a dynamically updated task–dataset knowledge graph from scientific literature using multi-agent extraction, entity resolution, and hybrid vector/graph retrieval. CS-TDS benchmarks task-oriented search; KATS outperforms RAG baselines in effectiveness and efficiency. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zixin Wei (Chinese University of Hong Kong)
- 2. Yucan Guo (Institute of Computing Technology, Chinese Academy of Sciences; School of Computer Science and Technology, University of Chinese Academy of Sciences)
- 3. Jinyang Li (University of Hong Kong)
- 4. Xiaolin Han (Northwestern Polytechnical University)
- 5. Xiaolong Jin (Institute of Computing Technology, Chinese Academy of Sciences; School of Computer Science and Technology, University of Chinese Academy of Sciences)
- 6. Chenhao Ma (Chinese University of Hong Kong)
BibTeX Citation
@article{wei_vldb26,
title = {{Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution}},
author = {Wei, Zixin and Guo, Yucan and Li, Jinyang and Han, Xiaolin and Jin, Xiaolong and Ma, Chenhao},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {5},
pages = {973--986},
doi = {10.14778/3796195.3796209},
url = {https://doi.org/10.14778/3796195.3796209},
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 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 878 | Table Union Search on Open Data | 2018 | VLDB | 0.00013463374 |
| 1,447 | Auctus: A Dataset Search Engine for Data Discovery and Augmentation | 2021 | VLDB | 0.00010760327 |
| 5,485 | Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System | 2025 | SIGMOD | 6.2013279e-05 |
| 6,094 | The Fast and the Private: Task-based Dataset Search | 2024 | CIDR | 5.9786215e-05 |
| 6,254 | In-depth Analysis of Graph-based RAG in a Unified Framework | 2025 | VLDB | 5.9405174e-05 |
| 13,314 | SemExplorer: A User Interface for Semantic Approach to Customized Dataset Search | 2025 | SIGMOD | - |
Previous
Page 1 / 1
Next