Dongfang Lou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Dongfang Lou has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Chao Zhang
Zhejiang University, Hangzhou, China
1 shared publication - Jinshu Lin
Hundsun Technologies Inc., Hangzhou, China
1 shared publication - Lu Chen
Zhejiang University, Hangzhou, China
1 shared publication - Yijiang Fan
Zhejiang University, Hangzhou, China
1 shared publication - Yu Mi
Zhejiang University, Hangzhou, China
1 shared publication - Yunjun Gao
Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 9 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 93-105
FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis
Text-to-SQL, which provides zero-code interface for operating relational databases, has gained much attention in financial analysis; because financial professionals may not be well-skilled in SQL programming. However, until now, there is no practical Text-to-SQL benchmark dataset for financial analysis, and existing Text-to-SQL methods have not considered the unique characteristics of databases in financial applications, such as commonly existing wide tables. To address these issues, we collect a practical Text-to-SQL benchmark dataset and propose a model-agnostic Large Language Model (LLMs)-based Text-to-SQL framework for financial analysis. The benchmark dataset, BULL, is collected from the practical financial analysis business of Hundsun Technologies Inc., including databases for fund, stock, and macro economy. Besides, the proposed LLMs-based Text-to-SQL framework, FinSQL, provides a systematic treatment for financial Text-to-SQL from the perspectives of prompt construction, parameter-efficient fine-tuning and output calibration. Experiments on BULL demonstrate that FinSQL achieves state-of-the-art performance at low cost, and it brings up to 36.64% improvement in few-shot cross-database scenarios.
- 9 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 93-105
Top Cited PapersOpen AccessFinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis
Text-to-SQL, which provides zero-code interface for operating relational databases, has gained much attention in financial analysis; because financial professionals may not be well-skilled in SQL programming. However, until now, there is no practical Text-to-SQL benchmark dataset for financial analysis, and existing Text-to-SQL methods have not considered the unique characteristics of databases in financial applications, such as commonly existing wide tables. To address these issues, we collect a practical Text-to-SQL benchmark dataset and propose a model-agnostic Large Language Model (LLMs)-based Text-to-SQL framework for financial analysis. The benchmark dataset, BULL, is collected from the practical financial analysis business of Hundsun Technologies Inc., including databases for fund, stock, and macro economy. Besides, the proposed LLMs-based Text-to-SQL framework, FinSQL, provides a systematic treatment for financial Text-to-SQL from the perspectives of prompt construction, parameter-efficient fine-tuning and output calibration. Experiments on BULL demonstrate that FinSQL achieves state-of-the-art performance at low cost, and it brings up to 36.64% improvement in few-shot cross-database scenarios.