Database
Bridge: Database-Grounded Interactive Disambiguation for Text-to-SQL
arXiv cs.DB0 views
arXiv:2611.17770v1 Announce Type: new Abstract: Ambiguity remains a persistent challenge in text-to-SQL, where an underspecified natural-language question may admit multiple plausible SQL interpretations. Recent work attempts to recover the user's intended interpretation through iterative clarification, but typically relies heavily on LLM parametric knowledge for ad hoc reasoning, leading to limited ambiguity-resolution effectiveness and high LLM cost. We further observe that many ambiguity errors stem from ambiguous column grounding, which remains poorly handled. Therefore, we propose Bridge, a database-grounded disambiguation framework built on an existing iterative protocol. Bridge supplies the LLM's ambiguity detection with offline-distilled knowledge about potential ambiguity relations among columns in the target database. Offline, Bridge constructs a Column Ambiguity Graph by first identifying potentially ambiguous column pairs using complementary database-grounded signals, followed by LLM-based verification. Online, columns and values mentioned in a previous incorrect SQL prediction are used as anchors to retrieve alternatives from the Column Ambiguity Graph and an offline-constructed value similarity index, respectively. The results are integrated for further pruning and consolidated for subsequent ambiguity detection. Extensive experiments on BIRD-dev without the benchmark-provided evidence show that, at comparable LLM cost, Bridge outperforms the strongest baseline by 11.60% in execution accuracy and improves the recall and precision of column usage in the final SQL by 5.25% and 12.37%, respectively.
Source:https://arxiv.org/abs/2611.17770PreviousUse-case-driven ontology modeling with the NeOn methodology for ambient assisted livingNextQuery Processing with eBPF-Offload on Computational Storage
Related posts
WordPress Bozuk Veritabanı Tablolarını phpMyAdmin ile Onarma
0dev.to Database
VerfGraph: Efficient Zero-Knowledge Verifiable Graph Query Evaluation System
0arXiv cs.CR
Ranking lifetime free credit cards by rupees returned
0dev.to WebDev
Technical Audits: What to Look For Before Series A
0dev.to WebDev
Finding two ClickHouse time zone bugs with a differential test
0dev.to Python
A dry run that left no trace - how a rollback in a Uniface form removed the service's own log entry
0dev.to