Saved in:
Bibliographic Details
Main Authors: Kim, Juhyeong, Kim, Yejin, Lee, Youngbin, Byun, Hyunwoo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.14162
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917028993957888
author Kim, Juhyeong
Kim, Yejin
Lee, Youngbin
Byun, Hyunwoo
author_facet Kim, Juhyeong
Kim, Yejin
Lee, Youngbin
Byun, Hyunwoo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14162
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API
Kim, Juhyeong
Kim, Yejin
Lee, Youngbin
Byun, Hyunwoo
Information Retrieval
Artificial Intelligence
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.
title FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2510.14162