BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases
Summary: BridgeScope modularizes SQL into fine-grained, LLM-friendly tools (context retrieval, CRUD, ACID transactions) and ties tool behavior to DB privileges and user policies to prevent unsafe/unauthorized operations and preempt infeasible tasks. A proxy mechanism bypasses LLM data-transfer bottlenecks for data‑intensive workflows; database-agnostic design with a PostgreSQL release cuts token usage up to 80%. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Lianggui Weng (Alibaba)
- 2. Dandan Liu (Alibaba)
- 3. Rong Zhu (Alibaba)
- 4. Bolin Ding (Alibaba)
- 5. Jingren Zhou (Alibaba)
BibTeX Citation
@inproceedings{weng_cidr26,
address = {Amsterdam, Netherlands},
series = {{CIDR} '26},
title = {{BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Weng, Lianggui and Liu, Dandan and Zhu, Rong and Ding, Bolin and Zhou, Jingren},
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 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 950 | CAESURA: Language Models as Multi-Modal Query Planners | 2024 | CIDR | 0.0001302491 |
| 2,099 | Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks | 2024 | SIGMOD | 9.1682353e-05 |
| 2,852 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB | 8.0455088e-05 |
| 4,809 | Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks | 2021 | SIGMOD | 6.4984309e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,199 | Automated Discovery of Test Oracles for Database Management Systems Using LLMs | 2026 | SIGMOD |
| 2 | 2,710 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD |
| 3 | 7,809 | Can Large Language Models Be Query Optimizer for Relational Databases? | 2026 | SIGMOD |
| 4 | 3,757 | Panda: Performance Debugging for Databases using LLM Agents | 2024 | CIDR |
| 5 | 9,542 | Database as Runtime: Compiling LLMs to SQL for In-database Model Serving | 2025 | SIGMOD |
| 6 | 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB |
| 7 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 8 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 9 | 9,391 | Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models | 2024 | VLDB |
| 10 | 11,024 | Horizon: Robust Checks for SQL Migration Using LLMs | 2025 | VLDB |