TACO: Token-Aware Context Optimization for Structured OpenStreetMap Query Generation
Summary: Introduces OsmNL, a human-curated benchmark for natural-language-to-OverpassQL generation, and models demonstration selection as budgeted, submodular subset mining. TACO balances relevance and structural diversity, achieving state-of-the-art accuracy while cutting token use by over 50%. (summarized by gpt-6-luna on Oct 22 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhuoyue Wan (Hong Kong Polytechnic University)
- 2. Wentao Hu (Hong Kong Polytechnic University)
- 3. Hwanhee Kim (Hong Kong Polytechnic University)
- 4. Chen Jason Zhang (Hong Kong Polytechnic University)
- 5. Shuaimin Li (Chinese Academy of Sciences; Shenzhen Institutes of Advanced Technology)
- 6. Yuanfeng Song (Independent)
- 7. Ming Deng (Hong Kong Polytechnic University)
- 8. Xiao-Yong Wei (Hong Kong Polytechnic University)
- 9. Raymond Chi-Wing Wong (Hong Kong University of Science and Technology)
BibTeX Citation
@inproceedings{wan_sigmod27,
title = {{TACO: Token-Aware Context Optimization for Structured OpenStreetMap Query Generation}},
author = {Wan, Zhuoyue and Hu, Wentao and Kim, Hwanhee and Zhang, Chen Jason and Li, Shuaimin and Song, Yuanfeng and Deng, Ming and Wei, Xiao-Yong and Wong, Raymond Chi-Wing},
series = {{SIGMOD} '27},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3837126},
url = {https://dl.acm.org/doi/10.1145/3837126},
year = {2027}
}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 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 163 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00027456647 |
| 501 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.00017239952 |
| 1,209 | CatSQL: Towards Real World Natural Language to SQL Applications | 2023 | VLDB | 0.00011499224 |
| 2,117 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB | 9.0012524e-05 |
| 2,216 | Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning | 2023 | SIGMOD | 8.8249841e-05 |
| 4,345 | Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks | 2021 | SIGMOD | 6.6388774e-05 |
| 8,096 | Two Birds with One Stone: Efficient Deep Learning over Mislabeled Data through Subset Selection | 2025 | SIGMOD | 5.3739121e-05 |
Previous
Page 1 / 1
Next