# JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling

arXiv: https://arxiv.org/abs/2505.14305 · HTML: https://mlsanity.com/paper/2505.14305/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 25 of 25)

- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [CHESS: Contextual Harnessing for Efficient SQL Synthesis](https://mlsanity.com/paper/2405.16755/) (2024)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [Liger Kernel: Efficient Triton Kernels for LLM Training](https://mlsanity.com/paper/2410.10989/) (2024)
- [Structure-Grounded Pretraining for Text-to-SQL](https://mlsanity.com/paper/2010.12773/) (2020)
- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [Towards Robustness of Text-to-SQL Models against Synonym Substitution](https://mlsanity.com/paper/2106.01065/) (2021)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation](https://mlsanity.com/paper/2405.07467/) (2024)
- [Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization](https://mlsanity.com/paper/2109.05157/) (2021)
- [A Survey on Employing Large Language Models for Text-to-SQL Tasks](https://mlsanity.com/paper/2407.15186/) (2024)
- [Synthesizing Text-to-SQL Data from Weak and Strong LLMs](https://mlsanity.com/paper/2408.03256/) (2024)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL](https://mlsanity.com/paper/2409.16751/) (2024)
- [Label Supervised LLaMA Finetuning](https://mlsanity.com/paper/2310.01208/) (2023)
- [Extractive Schema Linking for Text-to-SQL](https://mlsanity.com/paper/2501.17174/) (2025)
- [SQL-to-Schema Enhances Schema Linking in Text-to-SQL](https://mlsanity.com/paper/2405.09593/) (2024)
- [BASE-SQL: A powerful open source Text-To-SQL baseline approach](https://mlsanity.com/paper/2502.10739/) (2025)
- [DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL](https://mlsanity.com/paper/2503.04959/) (2025)

## Built on by (most cited first, 4 of 4)

- [SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation](https://mlsanity.com/paper/2604.06736/) (2026)
- [IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models](https://mlsanity.com/paper/2602.05385/) (2026)
- [ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL](https://mlsanity.com/paper/2606.05906/) (2026)
- [AttnLink: Turning Attention into Schema Links for Text-to-SQL](https://mlsanity.com/paper/2608.00693/) (2026)

## Abstract (arXiv)

Text-to-SQL, which maps natural language to SQL queries, has benefited greatly from recent advances in Large Language Models (LLMs). While LLMs offer various paradigms for this task, including prompting and supervised fine-tuning (SFT), SFT approaches still face challenges such as complex multi-stage pipelines and poor robustness to noisy schema information. To address these limitations, we present JOLT-SQL, a streamlined single-stage SFT framework that jointly optimizes schema linking and SQL generation via a unified loss. JOLT-SQL employs discriminative schema linking, enhanced by local bidirectional attention, alongside a confusion-aware noisy schema sampling strategy with selective attention to improve robustness under noisy schema conditions. Experiments on the Spider and BIRD benchmarks demonstrate that JOLT-SQL achieves state-of-the-art execution accuracy among comparable-size open-source models, while significantly improving both training and inference efficiency. Our code is available at https://github.com/Songjw133/JOLT-SQL.