Reliable Text-to-SQL with Adaptive Abstention

Summary: RTS adds adaptive abstention and human-in-the-loop for reliable text-to-SQL. Branching Point Prediction with conformal guarantees guides schema linking, and a small generator nearly matches larger models on BIRD, enabling robust, transparent DB interfaces. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h62f85e7d397cfbed
Venue: SIGMOD
Year: 2025
Pagerank: 5.6218378e-05
Overall Rank: 7,012 | 52.86%
DOI: 10.1145/3709719

Incoming Non-self Citations Over Time

Authors

1. Kaiwen Chen (University of Toronto)
2. Yueting Chen (Seattle University)
3. Nick Koudas (University of Toronto)
4. Xiaohui Yu (York University)

BibTeX Citation

@inproceedings{chen_sigmod25,
        title = {{Reliable Text-to-SQL with Adaptive Abstention}},
        author = {Chen, Kaiwen and Chen, Yueting and Koudas, Nick and Yu, Xiaohui},
        series = {{SIGMOD} '25},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3709719},
        url = {https://dl.acm.org/doi/10.1145/3709719},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,679	Relational Deep Dive: Error-Aware Queries Over Unstructured Data	2026	VLDB	5.2905577e-05
9,068	ST-Raptor: LLM-Powered Semi-Structured Table Question Answering	2026	SIGMOD	5.2283159e-05
10,432	DBugScribe: Automatic Database Bug Reproduction from Community Reports	2026	SIGMOD	4.9793485e-05
10,545	Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks	2026	SIGMOD	4.9793485e-05
11,160	RTS+: Reliable Text to SQL	2025	SIGMOD	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 6 of 6 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
174	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.00026790979
180	Constructing an Interactive Natural Language Interface for Relational Databases	2015	VLDB	0.0002654471
439	ATHENA: An Ontology-Driven System for Natural Language Querying over Relational Data Stores	2016	VLDB	0.00018251249
533	CodeS: Towards Building Open-source Language Models for Text-to-SQL	2024	SIGMOD	0.00016826571
1,356	CatSQL: Towards Real World Natural Language to SQL Applications	2023	VLDB	0.00010925509
3,282	A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems	2021	SIGMOD	7.4563046e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,738	OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision	2026	VLDB
2	10,780	SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL	2026	VLDB
3	3,489	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB
4	4,787	Hybrid Querying Over Relational Databases and Large Language Models	2025	CIDR
5	10,594	Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding	2026	SIGMOD
6	10,695	NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions	2026	VLDB
7	7,952	The Power of Constraints in Natural Language to SQL Translation	2025	VLDB
8	10,766	A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases	2026	VLDB
9	10,893	Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation	2026	VLDB
10	11,160	RTS+: Reliable Text to SQL	2025	SIGMOD