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

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.

arXiv commentWork in progress. Added results of advanced prompting strategies, e.g., CoT. (19 pages)

Cited by in corpus (7)

• Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
• Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
• CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
• CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts
• Cross-lingual Aspect-Based Sentiment Analysis: A Survey on Tasks, Approaches, and Challenges
• A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness
• Non-native speakers of English or ChatGPT: Who thinks better?