FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models

TL;DR

FinDABench is a comprehensive benchmark designed to evaluate the financial data analysis capabilities of large language models across foundational, reasoning, and technical skills, aiming to advance LLMs in finance.

Contribution

The paper introduces FinDABench, the first specialized benchmark for assessing LLMs' financial data analysis abilities across multiple dimensions.

Findings

Evaluates LLMs' numerical calculation and sentiment assessment skills.

Assesses models' ability to understand financial texts and detect anomalies.

Examines models' technical skills in data analysis and visualization.

Abstract

Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. However, their proficiency and reliability in the specialized domain of financial data analysis, particularly focusing on data-driven thinking, remain uncertain. To bridge this gap, we introduce \texttt{FinDABench}, a comprehensive benchmark designed to evaluate the financial data analysis capabilities of LLMs within this context. \texttt{FinDABench} assesses LLMs across three dimensions: 1) \textbf{Foundational Ability}, evaluating the models' ability to perform financial numerical calculation and corporate sentiment risk assessment; 2) \textbf{Reasoning Ability}, determining the models' ability to quickly comprehend textual information and analyze abnormal financial reports; and 3) \textbf{Technical Skill}, examining the models' use of technical knowledge to address real-world data analysis challenges involving analysis generation and charts visualization from multiple perspectives. We will release \texttt{FinDABench}, and the evaluation scripts at \url{https://github.com/cubenlp/BIBench}. \texttt{FinDABench} aims to provide a measure for in-depth analysis of LLM abilities and foster the advancement of LLMs in the field of financial data analysis.