Shaobin Shi — accepted AI-conference papers

2025

GenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQL

Zhifeng Hao, Junqi Huang, Shaobin Shi, Ruichu Cai, Boyan Xu

EMNLP 2025

Schema linking is widely recognized as a key factor in improving text-to-SQL performance. Supervised fine-tuning approaches enhance SQL generation quality by explicitly fine-tuning schema linking as an extraction task. However, they suffer from two major limitations: (i) The training corpus of small

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL

Bingfeng Chen, Shaobin Shi, Yongqi Luo, Boyan Xu, Ruichu Cai, Zhifeng Hao

NAACL 2025long

Generative language models have shown significant potential in single-turn Text-to-SQL. However, their performance does not extend equivalently to multi-turn Text-to-SQL. This is primarily due to generative language models’ inadequacy in handling the complexities of context information and dynamic s…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗