Is GPT-4 a Good Data Analyst?
Submission Type: Regular Long Paper
Submission Track: NLP Applications
Keywords: data analyst, GPT4
TL;DR: We quantitively evaluate whether GPT-4 is a good data analyst.
Abstract: As large language models (LLMs) have demonstrated their powerful capabilities in plenty of domains and tasks, including context understanding, code generation, language generation, data storytelling, etc., many data analysts may raise concerns if their jobs will be replaced by artificial intelligence (AI). This controversial topic has drawn great attention in public. However, we are still at a stage of divergent opinions without any definitive conclusion. Motivated by this, we raise the research question of "is GPT-4 a good data analyst?" in this work and aim to answer it by conducting head-to-head comparative studies. In detail, we regard GPT-4 as a data analyst to perform end-to-end data analysis with databases from a wide range of domains. We propose a framework to tackle the problems by carefully designing the prompts for GPT-4 to conduct experiments. We also design several task-specific evaluation metrics to systematically compare the performance between several professional human data analysts and GPT-4. Experimental results show that GPT-4 can achieve comparable performance to humans. We also provide in-depth discussions about our results to shed light on further studies before reaching the conclusion that GPT-4 can replace data analysts.
Submission Number: 2597
Loading