Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT

TL;DR

This study evaluates ChatGPT's understanding capabilities using the GLUE benchmark, comparing it with fine-tuned BERT models, and explores how prompting strategies can enhance its performance.

Contribution

It provides a quantitative analysis of ChatGPT's understanding ability across multiple NLP tasks and compares it with BERT models, highlighting strengths and weaknesses.

Findings

ChatGPT struggles with paraphrase and similarity tasks.

ChatGPT outperforms BERT on inference tasks.

Prompting strategies can improve ChatGPT's understanding.

Abstract

Recently, ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries. Several prior studies have shown that ChatGPT attains remarkable generation ability compared with existing models. However, the quantitative analysis of ChatGPT's understanding ability has been given little attention. In this report, we explore the understanding ability of ChatGPT by evaluating it on the most popular GLUE benchmark, and comparing it with 4 representative fine-tuned BERT-style models. We find that: 1) ChatGPT falls short in handling paraphrase and similarity tasks; 2) ChatGPT outperforms all BERT models on inference tasks by a large margin; 3) ChatGPT achieves comparable performance compared with BERT on sentiment analysis and question-answering tasks. Additionally, by combining some advanced prompting strategies, we show that the understanding ability of ChatGPT can be further improved.