Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909685410430976 |
|---|---|
| author | Wang, Anqi Yin, Zhizhuo Hu, Yulu Mao, Yuanyuan Han, Lei Tong, Xin Jiao, Keqin Hui, Pan |
| author_facet | Wang, Anqi Yin, Zhizhuo Hu, Yulu Mao, Yuanyuan Han, Lei Tong, Xin Jiao, Keqin Hui, Pan |
| contents | Large language models (LLMs) are increasingly integrated into creative coding, yet how users reflect, and how different co-creation conditions influence reflective behavior, remains underexplored. This study investigates situated, moment-to-moment reflection in creative coding under two prompting strategies: the entire task invocation (T1) and decomposed subtask invocation (T2), to examine their effects on reflective behavior. Our mixed-method results reveal three distinct reflection types and show that T2 encourages more frequent, strategic, and generative reflection, fostering diagnostic reasoning and goal redefinition. These findings offer insights into how LLM-based tools foster deeper creative engagement through structured, behaviorally grounded reflection support. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09750 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding Wang, Anqi Yin, Zhizhuo Hu, Yulu Mao, Yuanyuan Han, Lei Tong, Xin Jiao, Keqin Hui, Pan Human-Computer Interaction Artificial Intelligence J.5 Large language models (LLMs) are increasingly integrated into creative coding, yet how users reflect, and how different co-creation conditions influence reflective behavior, remains underexplored. This study investigates situated, moment-to-moment reflection in creative coding under two prompting strategies: the entire task invocation (T1) and decomposed subtask invocation (T2), to examine their effects on reflective behavior. Our mixed-method results reveal three distinct reflection types and show that T2 encourages more frequent, strategic, and generative reflection, fostering diagnostic reasoning and goal redefinition. These findings offer insights into how LLM-based tools foster deeper creative engagement through structured, behaviorally grounded reflection support. |
| title | Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding |
| topic | Human-Computer Interaction Artificial Intelligence J.5 |
| url | https://arxiv.org/abs/2402.09750 |