NL2SQLBench is a new modular benchmarking framework that evaluates LLM NL2SQL methods across three core modules on existing datasets, exposing large accuracy gaps and computational inefficiency.
Re-examining the Role of Schema Linking in Text-to- SQL
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5roles
background 2representative citing papers
EvoMQL uses iterative Draft-Refine-Optimize cycles with execution feedback to reach 76.6% accuracy on EAI and 83.1% on TEND benchmarks for natural language to MongoDB query generation.
SPENCE shows older NL2SQL benchmarks like Spider have high performance sensitivity to syntactic changes, indicating likely training contamination, while newer ones like BIRD show little sensitivity and appear largely clean.
PV-SQL boosts Text-to-SQL execution accuracy by 5% and valid efficiency by 20.8% on BIRD benchmarks via database probing and rule-based SQL verification while using fewer tokens.
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.
citing papers explorer
-
NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions
NL2SQLBench is a new modular benchmarking framework that evaluates LLM NL2SQL methods across three core modules on existing datasets, exposing large accuracy gaps and computational inefficiency.
-
Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation
EvoMQL uses iterative Draft-Refine-Optimize cycles with execution feedback to reach 76.6% accuracy on EAI and 83.1% on TEND benchmarks for natural language to MongoDB query generation.
-
SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks
SPENCE shows older NL2SQL benchmarks like Spider have high performance sensitivity to syntactic changes, indicating likely training contamination, while newer ones like BIRD show little sensitivity and appear largely clean.
-
PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents
PV-SQL boosts Text-to-SQL execution accuracy by 5% and valid efficiency by 20.8% on BIRD benchmarks via database probing and rule-based SQL verification while using fewer tokens.
-
Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.