mlsanityData to 13 Oct 2026

FINCH: Financial Intelligence using Natural language for Contextualized SQL Handling

arXiv 2510.01887 ↗First posted 2 Oct 2025q-fin.CP cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 18 of its 33 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

18 of 33 references.

References · 18

  1. 2020Scaling Laws for Neural Language Modelscited by 6,494
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,348
  3. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,133
  4. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 680
  5. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 553
  6. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 472
  7. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 422
  8. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 405
  9. 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answeringcited by 196
  10. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 182
  11. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 142
  12. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
6 more
  1. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  2. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 67
  3. 2024FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysiscited by 36
  4. 2022UniRPG: Unified Discrete Reasoning over Table and Text as Program Generationcited by 13
  5. 2024BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domaincited by 10
  6. 2025Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotationcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024FinBen: A Holistic Financial Benchmark for Large Language Models
  2. 2026FinForge: Semi-Synthetic Financial Benchmark Generation
  3. 2025Finance Language Model Evaluation (FLaME)
  4. 2024FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models
  5. 2025FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking
  6. 2023Beyond Classification: Financial Reasoning in State-of-the-Art Language Models
  7. 2025FinS-Pilot: A Benchmark for Online Financial RAG System
  8. 2025Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning