Abstract
Large language models (LLMs) with in-context learning have demonstrated impressive generalization capabilities in the cross-domain text-to-SQL task, without the use of in-domain annotations. However, incorporating in-domain demonstration examples has been found to greatly enhance LLMs’ performance. In this paper, we delve into the key factors within in-domain examples that contribute to the improvement and explore whether we can harness these benefits without relying on in-domain annotations. Based on our findings, we propose a demonstration selection framework, ODIS, which utilizes both out-of-domain examples and synthetically generated in-domain examples to construct demonstrations. By retrieving demonstrations from hybrid sources, ODIS leverages the advantages of both, showcasing its effectiveness compared to baseline methods that rely on a single data source. Furthermore, ODIS outperforms state-of-the-art approaches on two cross-domain text-to-SQL datasets, with improvements of 1.1 and 11.8 points in execution accuracy, respectively.- Anthology ID:
- 2023.findings-emnlp.944
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14174–14189
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.944
- DOI:
- 10.18653/v1/2023.findings-emnlp.944
- Cite (ACL):
- Shuaichen Chang and Eric Fosler-Lussier. 2023. Selective Demonstrations for Cross-domain Text-to-SQL. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14174–14189, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Selective Demonstrations for Cross-domain Text-to-SQL (Chang & Fosler-Lussier, Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.findings-emnlp.944.pdf