Database Paper Browser

Back to papers

Hybrid Querying Over Relational Databases and Large Language Models

Summary: Presents SWAN: the first cross-domain benchmark of 120 beyond-database questions over four real-world relational schemas for hybrid DB+LLM querying. Proposes schema-expansion and UDF-based integration, evaluates GPT‑4 Turbo (≤40% exec accuracy, 48.2% factuality) and exposes optimization needs and accuracy/factuality gaps. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
536
Venue
CIDR
Year
2025
Pagerank
6.1057096e-05
Overall Rank
4,529 | 68.53%
DOI
-

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
94 CrowdDB: Answering Queries with Crowdsourcing 2011 SIGMOD 0.00051273089
118 Answering Queries using Humans, Algorithms and Databases 2011 CIDR 0.00045860394
185 DuckDB: an Embeddable Analytical Database 2019 SIGMOD 0.00036529607
246 Crowdsourced Databases: Query Processing with People 2011 CIDR 0.00030952631
366 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 2024 VLDB 0.00025580097
516 Can Foundation Models Wrangle Your Data? 2023 VLDB 0.00021194444
2,331 Obtaining Complete Answers from Incomplete Databases 1996 VLDB 9.019917e-05
2,814 Deco: A System for Declarative Crowdsourcing 2012 VLDB 8.0807229e-05
2,987 NL2SQL is a solved problem... Not! 2024 CIDR 7.77529e-05
3,803 Revisiting Prompt Engineering via Declarative Crowdsourcing 2024 CIDR 6.7498941e-05
8,489 What Should A Database Know? 1988 PODS 4.4951061e-05
Previous Page 1 / 1 Next

Semantically Similar Papers