SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligence
Summary: SiriusBI is an industrial LLM-BI system combining coordinated modules with multi-round semantic clarification, knowledge-guided dialogue, and proactive querying beyond one-shot SQL generation. Its data-conditioned method selection enables efficient fine-tuning or low-cost cross-domain SIR-based generation, achieving 93%+ accuracy in deployment. (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. Jie Jiang (Tencent)
- 2. Haining Xie (Tencent)
- 3. Siqi Shen (Peking University)
- 4. Yu Shen (Tencent)
- 5. Zihan Zhang (Tencent)
- 6. Meng Lei (Tencent)
- 7. Yifeng Zheng (Tencent)
- 8. Yang Li (Tencent)
- 9. Chunyou Li (Tencent)
- 10. Danqing Huang (Tencent)
- 11. Yinjun Wu (Peking University)
- 12. Wentao Zhang (Peking University)
- 13. Bin Cui (Peking University)
- 14. Peng Chen (Tencent)
BibTeX Citation
@article{jiang_vldb25,
title = {{SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligence}},
author = {Jiang, Jie and Xie, Haining and Shen, Siqi and Shen, Yu and Zhang, Zihan and Lei, Meng and Zheng, Yifeng and Li, Yang and Li, Chunyou and Huang, Danqing and Wu, Yinjun and Zhang, Wentao and Cui, Bin and Chen, Peng},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {12},
pages = {4860--4873},
doi = {10.14778/3750601.3750610},
url = {https://doi.org/10.14778/3750601.3750610},
year = {2025}
}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 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 37 | DISCOVER: Keyword Search in Relational Databases | 2002 | VLDB | 0.00048017193 |
| 179 | Constructing an Interactive Natural Language Interface for Relational Databases | 2015 | VLDB | 0.00026838277 |
| 212 | Efficient IR-Style Keyword Search over Relational Databases | 2003 | VLDB | 0.000247733 |
| 756 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.0001431656 |
| 930 | SPARK: Top-k Keyword Query in Relational Databases | 2007 | SIGMOD | 0.0001312728 |
| 2,039 | ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems | 2024 | VLDB | 9.2721259e-05 |
| 2,079 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | 2020 | SIGMOD | 9.2060425e-05 |
| 2,602 | NL2SQL is a solved problem... Not! | 2024 | CIDR | 8.3535452e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,433 | Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization | 2026 | SIGMOD |
| 2 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 3 | 6,259 | R-Bot: An LLM-based Query Rewrite System | 2025 | VLDB |
| 4 | 4,944 | Hybrid Querying Over Relational Databases and Large Language Models | 2025 | CIDR |
| 5 | 10,118 | Rethinking Analytical Processing in the GPU Era | 2026 | CIDR |
| 6 | 11,025 | A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code | 2025 | VLDB |
| 7 | 10,705 | Andromeda: Debugging Database Performance Issues with Retrieval-Augmented Large Language Models | 2025 | SIGMOD |
| 8 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 9 | 11,013 | Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models | 2025 | VLDB |
| 10 | 8,906 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |