Dreaming with ChatGPT: Unraveling the Challenges of LLMs Dream Generation
Abstract: Large Language Models (LLMs), such as ChatGPT, are used daily for different human-like text generation tasks. This motivates us to ask: Can an LLM generate human dreams? For this research, we explore this new avenue through the lens of ChatGPT, and its ability to generate valid dreams. We have three main findings: (i) Chatgpt-4o, the new version of chatGPT, generated all requested dreams. (ii) Generated dreams meet key psychological criteria of dreams. (iii) Generated dreams embed biases towards different groups. We hope our work will set the stage for developing a new task of dream generation for LLMs. This task can help psychologists evaluate patients' dreams based on their demographic factors.
Paper Type: Short
Research Area: Computational Social Science and Cultural Analytics
Research Area Keywords: human-computer interaction, language/cultural bias analysis
Contribution Types: Data resources, Data analysis
Languages Studied: English
Submission Number: 1114
Loading