Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-Shot Text-to-SQL Learning with Auxiliary Task
Shuaichen Chang, Pengfei Liu, Yun Tang, Jing Huang, Xiaodong He, Bowen Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add attentive pooling to the generation model (ablation) | Gen-model · WikiSQL full test | ACC_sel: 93.0% -> 94.2% | Improved |
| Add attentive pooling to the generation model (ablation) | Gen-model · WikiSQL full test | ACC_qm: 72.8% -> 73.5% | Improved |
| Add attentive pooling to the generation model (ablation) | Gen-model · WikiSQL full test | ACC_ex: 79.4% -> 80.1% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL full test | ACC_where: 84.8% -> 86.7% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL full test | ACC_qm: 73.5% -> 75.0% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL full test | ACC_ex: 80.1% -> 81.7% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL zero-shot test (W-0) | ACC_qm: +4.9% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL zero-shot test (W-0) | ACC_ex: +4.4% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL zero-shot test (W-0) | ACC_where: +3.6% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL zero-shot conditions with unseen column names | WHERE accuracy: 4.2% | Improved |
| Add auxiliary question-value-to-column mapping task (ablation) | Gen-model · WikiSQL zero-shot conditions with seen column names | WHERE accuracy: 2.1% | Improved |
| Enhance the encoder/decoder with bi-attention and attentive pooling | COARSE2FINE · WikiSQL full test | ACC_ex: +1.6% | Improved |
Closest papers by meaning
- Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search (ICML 2025 · similarity 0.89)
- ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL (ICLR 2025 · similarity 0.87)
- CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation (AAAI 2025 · similarity 0.87)
- Confidence Estimation for Error Detection in Text-to-SQL Systems (AAAI 2025 · similarity 0.87)
- SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
