Papers by Shaoming Duan
AFT-Tab: Adversarial Fine-Tuning for Tabular Data Synthesis with Long Text Columns (2026.acl-long)
Copied to clipboard
| Challenge: | Existing tabular data synthesis methods fail to account for cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns. |
| Approach: | They propose a framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator to quantify cross-modal semantic alignment. |
| Outcome: | The proposed framework outperforms state-of-the-art frameworks in fidelity, diversity, and task utility. |
TS-SQL: Test-driven Self-refinement for Text-to-SQL (2025.findings-emnlp)
Copied to clipboard
| Challenge: | null |
| Approach: | null |
| Outcome: | null |
DSQG-Syn: Synthesizing High-quality Data for Text-to-SQL Parsing by Domain Specific Question Generation (2025.findings-naacl)
Copied to clipboard
Shaoming Duan, Youxuan Wu, Chuanyi Liu, Yuhao Zhang, Zirui Wang, Peiyi Han, Shengyuan Yu, Liang Yan, Yingwei Liang
| Challenge: | Existing methods for generating SQL queries using natural language questions produce inconsistent NLQ-SQL pairs. |
| Approach: | They propose a text-to-SQL data synthesis framework that generates domain-relevant questions . they synthesize NLQ-SqL pairs that are domain-specific and intent-consistent . |
| Outcome: | The proposed method outperforms closed-source LLMs on the Text-to-SQL task. |
SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for self-play fine-tuning do not generate new information and the large number of correct SQL queries produced by the opponent model reduces the main model’s ability to generate accurate SQL queries. |
| Approach: | They propose a self-play fine-tuning method tailored for the Text-to-SQL task that synthesizes high-quality fine- tuning data iteratively based on the database schema and validation feedback to enhance model performance. |
| Outcome: | The proposed method outperforms existing state-of-the-art methods on six open-source LLMs and five widely used benchmarks. |