SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligence
Summary: SiriusBI: end-to-end LLM-powered BI that integrates coordinated modules and a multi-round dialogue (completion, knowledge-guided clarification, proactive querying) to overcome single-shot SQL and legacy BI gaps. Data-conditioned SQL generation picks one-step fine-tune or two-step Semantic IR for low-cost cross-domain transfer; production deployment yields >93% SQL accuracy and large analyst speedups. (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. Jie Jiang
- 2. Haining Xie
- 3. Siqi Shen
- 4. Yu Shen
- 5. Zihan Zhang
- 6. Meng Lei
- 7. Yifeng Zheng
- 8. Yang Li
- 9. Chunyou Li
- 10. Danqing Huang
- 11. Yinjun Wu
- 12. Wentao Zhang
- 13. Bin Cui
- 14. Peng Chen
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 |
|---|---|---|---|---|
| 54 | DISCOVER: Keyword Search in Relational Databases | 2002 | VLDB | 0.00066047203 |
| 206 | Constructing an Interactive Natural Language Interface for Relational Databases | 2015 | VLDB | 0.00034667032 |
| 276 | Efficient IR-Style Keyword Search over Relational Databases | 2003 | VLDB | 0.00029336949 |
| 998 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.00014729379 |
| 1,201 | SPARK: Top-k Keyword Query in Relational Databases | 2007 | SIGMOD | 0.0001334371 |
| 2,321 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | 2020 | SIGMOD | 9.03609e-05 |
| 2,433 | ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems | 2024 | VLDB | 8.8285962e-05 |
| 2,988 | NL2SQL is a solved problem... Not! | 2024 | CIDR | 7.7761714e-05 |
Previous
Page 1 / 1
Next