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

[李子通]

Hi Adapters,

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 the paper "Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT" (Got 13 cites since Feb 23), the authors 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. They 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, the authors show that the understanding ability of ChatGPT can be further improved.

Wish you would like it!

Time: Wed 4:00 pm

Venue: SEIEE 3-404

Best wishes,

Zitong