Winner of the Korean Society of Designers 2024 Spring Undergraduate Student Design Presentation Competition (DSUS) / Industrial Design students
- 24.08.19 / 박서연
Kang Soo Jeong, Hyun Dong Hee, Park Ga On, Seo Ye Rin, and Lee Ji Yoon, students from the Department of Industrial Design, participated in the 2024 Spring Collegiate Design Conference held at Yonsei University and presented a paper titled “Classification of Usage Behavior for Personalization of LLM Interface: Focusing on GPT-4” and won an excellent award.
The students captured the need to improve interactive interfaces in chat format from the LLM perspective with the emergence of GPT models, and conducted research with the essential goal of improving the interface of LLM models. They recruited users of GPT-4, which is widely used among LLM models, and through online surveys, observations, and interviews, they classified users' usage behaviors of LLM models according to the types of chat rooms they use, and proposed guidelines for improving the interface accordingly.
|
This content is translated from Korean to English using the AI translation service DeepL and may contain translation errors such as jargon/pronouns. If you find any, please send your feedback to kookminpr@kookmin.ac.kr so we can correct them.
|
|
Winner of the Korean Society of Designers 2024 Spring Undergraduate Student Design Presentation Competition (DSUS) / Industrial Design students |
||||
|---|---|---|---|---|
|
2024-08-19
748
Kang Soo Jeong, Hyun Dong Hee, Park Ga On, Seo Ye Rin, and Lee Ji Yoon, students from the Department of Industrial Design, participated in the 2024 Spring Collegiate Design Conference held at Yonsei University and presented a paper titled “Classification of Usage Behavior for Personalization of LLM Interface: Focusing on GPT-4” and won an excellent award.
The students captured the need to improve interactive interfaces in chat format from the LLM perspective with the emergence of GPT models, and conducted research with the essential goal of improving the interface of LLM models. They recruited users of GPT-4, which is widely used among LLM models, and through online surveys, observations, and interviews, they classified users' usage behaviors of LLM models according to the types of chat rooms they use, and proposed guidelines for improving the interface accordingly.
|
||||
