arXiv Machine Learning
FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 6
RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning
arXiv:2601. 05451v2 Announce Type: replace Abstract: Recent advances in text-to-SQL have been driven by larger models, better datasets, and new training methods like RLVR.
arXiv AI
Oct 2
Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying
Build2SPARQL is a large-scale benchmark dataset for translating natural-language questions into SPARQL queries over building knowledge graphs. The dataset is generated by a KG‑grounded pipeline that produces 6,136 executable SPARQL queries and 30,680 corresponding natural-language questions across six query-pattern families and five vocabulary registers, covering 201 building KGs. Human validation shows high semantic fidelity, naturalness, and operational plausibility, and retrieval‑augmented evaluation demonstrates significant accuracy gains for open‑weight language models.
arXiv AI
Jun 9
UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL
arXiv:2606. 08018v1 Announce Type: new Abstract: Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects.
arXiv AI
Sep 10
SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation
arXiv:2609.08950v1 Announce Type: cross Abstract: Text-to-SQL systems translate natural language queries into executable SQL, democratizing access to structured data. Despite recent advances driven b...
arXiv AI
Sep 23
LIMIT: Less Is More for Instruction Tuning in Text-to-SQL
LIMIT (Less Is More for Instruction Tuning in Text-to-SQL) challenges the belief that large instruction corpora are necessary for effective Text-to-SQL models. The framework uses a four‑stage data‑centric process—difficulty‑aware filtering, chain‑of‑thought synthesis, LLM‑as‑judge quality scoring, and genetic algorithm optimization—to select a compact set of examples that still achieve full schema coverage. On the BIRD and Spider benchmarks, LIMIT’s 796 and 863 samples enable Qwen3‑8B to reach 69.1% and 88.9% execution accuracy, outperforming methods trained on twenty times more data and setting a new state‑of‑the‑art for open‑source approaches.
arXiv AI
Sep 1
BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations
arXiv:2608.29345v1 Announce Type: new Abstract: While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user querie...