FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API

2025/10/15 by Kim, Juhyeong, Kim, Yejin, Lee, Youngbin +1
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2510.14162

Abstract

We present FinAI Data Assistant, a practical approach for natural-language querying over financial databases that combines large language models (LLMs) with the OpenAI Function Calling API. Rather than synthesizing complete SQL via text-to-SQL, our system routes user requests to a small library of vetted, parameterized queries, trading generative flexibility for reliability, low latency, and cost efficiency. We empirically study three questions: (RQ1) whether LLMs alone can reliably recall or extrapolate time-dependent financial data without external retrieval; (RQ2) how well LLMs map company names to stock ticker symbols; and (RQ3) whether function calling outperforms text-to-SQL for end-to-end database query processing. Across controlled experiments on prices and fundamentals, LLM-only predictions exhibit non-negligible error and show look-ahead bias primarily for stock prices relative to model knowledge cutoffs. Ticker-mapping accuracy is near-perfect for NASDAQ-100 constituents and high for S&P~500 firms. Finally, FinAI Data Assistant achieves lower latency and cost and higher reliability than a text-to-SQL baseline on our task suite. We discuss design trade-offs, limitations, and avenues for deployment.

Citations

• LLM-Enhanced Black-Litterman Portfolio Optimization
• Large Language Model Enhanced Text-to-SQL Generation: A Survey
• A Survey on Employing Large Language Models for Text-to-SQL Tasks
• Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL
• Large Language Models Are Zero-Shot Time Series Forecasters
• Gorilla: Large Language Model Connected with Massive APIs
• DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
• BloombergGPT: A Large Language Model for Finance
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
• SmBoP: Semi-autoregressive Bottom-up Semantic Parsing
• RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL\n Parsers
• CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
• Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVED

Related

• FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data
• FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis
• FinBen: A Holistic Financial Benchmark for Large Language Models
• FinStat2SQL: A Text2SQL Pipeline for Financial Statement Analysis
• Financial Analysis: Intelligent Financial Data Analysis System Based on LLM-RAG