Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages

2025-06-01 · Yongdong chi, Hanqing Wang, Zonghan Yang, Jian Yang, Xiao Yan, Yun Chen, Guanhua Chen

Text-to-SQL transforms the user queries from natural language to executable SQL programs, enabling non-experts to interact with complex databases. Existing prompt-based methods craft meticulous text guidelines and examples to facilitate SQL generation, but their accuracy is hindered by the large semantic gap between the texts and the low-resource SQL programs. In this work, we propose Pi-SQL, which incorporates the high-resource Python program as a pivot to bridge between the natural language query and SQL program. In particular, Pi-SQL first generates Python programs that provide fine-grained step-by-step guidelines in their code blocks or comments, and then produces an SQL program following the guidance of each Python program. The final SQL program matches the reference Python program's query results and, through selection from candidates generated by different strategies, achieves superior execution speed, with a reward-based valid efficiency score up to 4.55 higher than the best-performing baseline. Extensive experiments demonstrate the effectiveness of Pi-SQL, which improves the execution accuracy of the best-performing baseline by up to 3.20.

📄 PDF Abstract BibTeX arXiv:2506.00912

Code (0)

등록된 구현이 없습니다.

Tasks

Text to SQL Text-To-SQLvalid

Leveraging Text Guidance for Enhancing Demographic Fairness in Gender Classification

2025-12-11 · Anoop Krishnan arxiv

In the quest for fairness in artificial intelligence, novel approaches to enhance it in facial image based gender classification algorithms using text guided methodologies are presented. The core methodology involves lev…

Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation

2025-07-17 · Hanlei Shi, Leyuan Qu, Yu Liu, Di Gao 외 arxiv

Emotional talking-head generation has emerged as a pivotal research area at the intersection of computer vision and multimodal artificial intelligence, with its core value lying in enhancing human-computer interaction th…

Talking Head Generation Semantic Parsing

Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance

2026-08-04 · Xiucong Zhao, Jindong Tian, Hao Miao arxiv

Forecasting precise future motion of surrounding agents is essential for reliable autonomous vehicles. However, as the demand for longer prediction horizons increases, existing endpoint-completion or iterative-refine met…

Trajectory Prediction Autonomous Vehicles

FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models

2024-05-08 · CVPR 2024 1 · Jinglin Xu, Yijie Guo, Yuxin Peng

The 3D Human Pose Estimation (3D HPE) task uses 2D images or videos to predict human joint coordinates in 3D space. Despite recent advancements in deep learning-based methods, they mostly ignore the capability of couplin…

3D Human Pose Estimation Denoising Pose Estimation Prompt Learning

Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling

2025-11-11 · Jiale Liu, Haoming Zhou, Yishu Liu, Bingzhi Chen 외 arxiv

Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment,…

Vision-Language Navigation Visual Question Answering Image Captioning