Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution
Summary: Task-oriented dataset search from scientific literature: KATS builds a dynamically updatable task–dataset KG via multi-agent extraction, resolving task/dataset/entity ambiguity. New CS-TDS benchmark + hybrid vector+graph ranking yield large gains over RAG baselines. (summarized by gpt-5.4-mini on Apr 12 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zixin Wei
- 2. Yucan Guo
- 3. Jinyang Li
- 4. Xiaolin Han
- 5. Xiaolong Jin
- 6. Chenhao Ma
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 |
|---|---|---|---|---|
| 1,178 | Table Union Search on Open Data | 2018 | VLDB | 0.00013468118 |
| 1,751 | Auctus: A Dataset Search Engine for Data Discovery and Augmentation | 2021 | VLDB | 0.00010683295 |
| 6,077 | The Fast and the Private: Task-based Dataset Search | 2024 | CIDR | 5.2229324e-05 |
| 6,217 | Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System | 2025 | SIGMOD | 5.1534752e-05 |
| 7,931 | In-depth Analysis of Graph-based RAG in a Unified Framework | 2025 | VLDB | 4.613363e-05 |
| 13,109 | SemExplorer: A User Interface for Semantic Approach to Customized Dataset Search | 2025 | SIGMOD | - |
Previous
Page 1 / 1
Next