Exploring GPT-3 Model's Capability in Passing the Sally-Anne Test A Preliminary Study in Two Languages
Ze-nan DOU · 2023
This study aimed to investigate the capability of GPT-3 in passing the Sally-Anne test in two languages: Chinese and English. Three experiments were conducted to evaluate the model's performance under different questioning prompts. The results showed that with appropriate prompts, the model was able to consistently pass the test. The findings highlight the sensitivity of GPT-3 to different prompts and demonstrate the potential for using large language models as research subjects. This study sheds light on the similarities between human and AI reasoning and could contribute to further advancements in human-like AI development. It also encourages psychologists to expand their research interests to include AI.