FINCH: Financial Intelligence using Natural language for Contextualized SQL Handling
This addresses a critical gap for researchers and practitioners in finance by enabling more accurate and reliable natural language querying of financial databases, though it is incremental as it builds on existing Text-to-SQL methods.
The paper tackles the lack of a dedicated large-scale dataset for financial Text-to-SQL by introducing FINCH, a curated dataset with 292 tables and 75,725 natural language-SQL pairs, and proposes a finance-oriented evaluation metric for better performance assessment.
Text-to-SQL, the task of translating natural language questions into SQL queries, has long been a central challenge in NLP. While progress has been significant, applying it to the financial domain remains especially difficult due to complex schema, domain-specific terminology, and high stakes of error. Despite this, there is no dedicated large-scale financial dataset to advance research, creating a critical gap. To address this, we introduce a curated financial dataset (FINCH) comprising 292 tables and 75,725 natural language-SQL pairs, enabling both fine-tuning and rigorous evaluation. Building on this resource, we benchmark reasoning models and language models of varying scales, providing a systematic analysis of their strengths and limitations in financial Text-to-SQL tasks. Finally, we propose a finance-oriented evaluation metric (FINCH Score) that captures nuances overlooked by existing measures, offering a more faithful assessment of model performance.