Results 91 to 100 of about 8,163 (222)

DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework

Large language models (LLMs) have advanced Text-to-SQL, yet existing solutions still fall short of system-level reliability. The limitation is not merely in individual modules - e.g., schema linking, reasoning, and verification - but more critically in the lack of structured orchestration that enforces correctness across the entire workflow.
Li, Boyan, Chen, Chong, Xue, Zhujun, Mei, Yinan, Luo, Yuyu   +4 more
openaire   +2 more sources

Rationalization Models for Text-to-SQL

Published at ICLR 2025 Workshop on Reasoning and Planning for ...
Rossiello, Gaetano, Pham, Nhan, Glass, Michael, Lee, Junkyu, Subramanian, Dharmashankar   +4 more
openaire   +2 more sources

HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integration

2025 International Joint Conference on Neural Networks (IJCNN)
Text-to-SQL generation bridges the gap between natural language and databases, enabling users to query data without requiring SQL expertise. While large language models (LLMs) have significantly advanced the field, challenges remain in handling complex queries that involve multi-table joins, nested conditions, and intricate operations. Existing methods
Parab, Ganesh, Ahmad, Zishan, Birru, Dagnachew   +2 more
openaire   +2 more sources

Refining Zero-Shot Text-to-SQL Benchmarks via Prompt Strategies with Large Language Models

Applied Sciences
Text-to-SQL leverages large language models (LLMs) for natural language database queries, yet existing benchmarks like BIRD (12,751 question–SQL pairs, 95 databases) suffer from inconsistencies—e.g., 30% of queries misalign with SQL outputs—and ...
Ruikang Zhou, Fan Zhang
doaj   +1 more source

SE-HCL: Schema Enhanced Hybrid Curriculum Learning for Multi-Turn Text-to-SQL

IEEE Access
Existing multi-turn Text-to-SQL approaches, mainly use data in a randomized order when training the model, ignoring the rich structural information contained in the dialog and schema.
Yiyun Zhang, Sheng'an Zhou, Gengsheng Huang   +2 more
doaj   +1 more source

SQL-to-Text Generation with Graph-to-Sequence Model [PDF]

, 2018
Kun Xu, Lingfei Wu, Zhiguo Wang, Yansong Feng, Vadim Sheinin   +4 more
openalex   +1 more source

Combining computational linguistics with sentence embedding to create a zero-shot NLIDB

Array
Accessing relational databases using natural language is a challenging task, with existing methods often suffering from poor domain generalization and high computational costs. In this study, we propose a novel approach that eliminates the training phase
Yuriy Perezhohin, Fernando Peres, Mauro Castelli   +2 more
doaj   +1 more source

On the Structural Generalization in Text-to-SQL [PDF]

, 2023
Jieyu Li, Lu Chen, Ruisheng Cao, Zhu Su, Hongshen Xu, Zhi Chen, Hanchong Zhang, Kai Yu   +7 more
openalex   +1 more source

Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies [PDF]

Association for Computational Linguistics 2025, Chandarana, Yash Kaushikbhai, Gupta, Chirag, Liu, Terrance, Preotiuc-Pietro, Daniel, Wang, Shuyi   +5 more
openalex   +2 more sources

OPTIC—OPtimized Translation and Interaction for Cloud-Costs: Use of FOCUS Standardization and LLM Integration for Cloud Billing Analysis

IEEE Access
Managing billing data across multicloud environments remains a significant challenge due to heterogeneous data formats, fragmented cost metrics, and the technical complexity of cost analysis.
Gilberto N. Junior, Cesar Marcon
doaj   +1 more source