Applying large, proprietary API-based language models to text-to-SQL tasks poses a significant industry challenge: reliance on massive, schema-heavy prompts results in prohibitive per-token API costs and high latency, hindering scalable production deployment. We present a specialized, self-hosted 8B-parameter model designed for a conversational bot in CriQ, a sister app to Dream11, India's largest fantasy sports platform with over 250 million users, that answers user queries about cricket statistics. Our novel two-phase supervised fine-tuning approach enables the model to internalize the entire database schema, eliminating the need for long-context prompts. This reduces input tokens by over 99%, from a 17k-token baseline to fewer than 100, and replaces costly external API calls with efficient local inference. The resulting system achieves 98.4% execution success and 92.5% semantic accuracy, substantially outperforming a prompt-engineered baseline using Google's Gemini Flash 2.0 (95.6% execution, 89.4% semantic accuracy). These results demonstrate a practical path toward high-precision, low-latency text-to-SQL applications using domain-specialized, self-hosted language models in large-scale production environments.
EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
School of Software Technology, Zhejiang University(浙江大学软件学院);State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室);Tencent TEG(腾讯TEG);School of Mathematical Sciences, Peking University(北京大学数学科学学院)
DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph
Department of Artificial Intelligence, Sungkyunkwan University(人工智能系,成均馆大学);Department of Immersive Media Engineering, Sungkyunkwan University(沉浸媒体工程系,成均馆大学);Department of Computer Science and Engineering, Sungkyunkwan University(计算机科学与工程系,成均馆大学)
Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL
School of Computer Science, Guangdong University of Technology(广东技术大学计算机科学学院);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东人工智能与数字经济实验室);Peng Cheng Laboratory(鹏城实验室);College of Science, Shantou University(汕头大学理学院)
PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency
SenseTime Research(商汤科技研究院);Peking University(北京大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机学院);University of Cologne(科隆大学)
S$^2$SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers
Alibaba Group(阿里巴巴集团);University of Chinese Academy of Sciences(中国科学院大学);The Chinese University of Hong Kong(香港中文大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Center for Data Science, Peking University(北京大学数据科学中心);The MOE Key Laboratory of Computational Linguistics, Peking University(北京大学教育部计算语言学重点实验室)
LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL
China Academy of Information and Communications Technology(中国信息通信技术研究院);Renmin University of China(中国人民大学);University of International Business and Economics(国际经济贸易大学)
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
School of Computer Science, Guangdong University of Technology(广东工业大学计算机学院);Peng Cheng Laboratory(鹏城实验室);College of Science, Shantou University(汕头大学理学院)
STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing
University of Science and Technology of China(中国科学技术大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)
Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing
University of Chinese Academy of Sciences(中国科学院大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Alibaba Group(阿里巴巴集团);Massachusetts Institute of Technology(麻省理工学院)
Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents
School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院);Big Data Shortage and Management, MIIT(工业和信息化部大数据短缺与管理局);School of Computing, National University of Singapore(新加坡国立大学计算机学院);School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算与信息系统学院)