arXiv Computation and Language August 25, 2026 By Yingnan Chen, Chun Ding, Tianshi Xu, Xu Yang, Si Wu

SPOC-SQL: Stage-wise Preference Optimization for Controllable Text-to-SQL

Read the original on arXiv Computation and Language →

SPOC-SQL introduces a stage-wise approach to Text-to-SQL, breaking the task into four sequential subtasks aligned with standard SQL execution logic. It applies fine-grained preference optimization at key decision points and a structured decomposition strategy, enabling explicit intermediate representations for stage-wise intervention and correction. The method yields more controllable and reliable SQL generation, with experiments showing that incorporating stage-wise human knowledge consistently improves performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

data-engineering

Hugging Face Trending Papers

Aug 24

SPOC-SQL: Stage-wise Preference Optimization for Controllable Text-to-SQL

Text-to-SQL aims to translate natural language questions into executable SQL queries over relational databases, requiring multi-stage structured reasoning over database schemas and query constraints....

data-engineering

arXiv Machine Learning

Jun 15

Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards

arXiv:2505. 04671v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) trained with reinforcement learning (RL) have improved Text-to-SQL performance.

By Yuxin Zhang, Meihao Fan, Ju Fan, Mingyang Yi, Yuyu Luo, Guoliang Li, Bin Wu, Wenchao Zhou

llms reinforcement-learning safety data-engineering

arXiv AI

Jun 16

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

arXiv:2606. 15598v1 Announce Type: new Abstract: Text-to-SQL aims to translate natural language questions into executable SQL queries over structured databases, enabling non-expert users to access data intuitively.

By Feng Lyu, Jinfeng Cen, Sijing Duan, Hao Wu, Shucheng Li, Weixu Zhang, Haolun Wu

llms fine-tuning benchmarks data-engineering

arXiv AI

Jun 8

Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards

arXiv:2606. 06825v1 Announce Type: cross Abstract: Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined over a single SQL state.

By Shihao Zhang, Xiaoman Wang, Yuan Liu, Yunshi Lan, Weining Qian

llms reinforcement-learning safety data-engineering

arXiv AI

2d ago

Replacing Training with Memory: Listwise Selection for Text-to-SQL

The paper proposes a fine‑tuning‑free listwise selector for Text‑to‑SQL systems that replaces traditional learning objectives with inference‑time strategies. It introduces reusable structured memories (MaP‑SQL) that encode mappings from natural language to schema elements, SQL operations, and expected outputs, and uses these memories to evaluate candidate queries. To reduce positional bias, the method aggregates rankings across multiple input permutations, optimizing inference cost through execution results and pointwise scoring. The approach achieves higher selection accuracy, fewer unnecessary comparisons, and outperforms the prior state‑of‑the‑art R^3‑SQL on the BIRD‑dev benchmark while using fewer tokens.

By Yeonseok Jeong, Soyoung Yoon, Seongjun Lee, Seung-won Hwang

llms fine-tuning benchmarks safety data-engineering

arXiv AI

Jul 1

Test-Time Verification for Text-to-SQL via Outcome Reward Models

arXiv:2606. 30851v1 Announce Type: cross Abstract: Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL.

By Mattia Tritto, Giuseppe Farano, Dario Di Palma, Gaetano Rossiello, Fedelucio Narducci, Dharmashankar Subramanian, Tommaso Di Noia

llms benchmarks safety data-engineering

One email a morning, machine-written

Related stories

SPOC-SQL: Stage-wise Preference Optimization for Controllable Text-to-SQL

Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards

Replacing Training with Memory: Listwise Selection for Text-to-SQL

Test-Time Verification for Text-to-SQL via Outcome Reward Models