Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models

要旨

Advances in language modeling have paved the way for novel human-AI co-writing experiences. This paper explores how varying levels of scaffolding from large language models (LLMs) shape the co-writing process. Employing a within-subjects field experiment with a Latin square design, we asked participants (N=131) to respond to argumentative writing prompts under three randomly sequenced conditions: no AI assistance (control), next-sentence suggestions (low scaffolding), and next-paragraph suggestions (high scaffolding). Our findings reveal a U-shaped impact of scaffolding on writing quality and productivity (words/time). While low scaffolding did not significantly improve writing quality or productivity, high scaffolding led to significant improvements, especially benefiting non-regular writers and less tech-savvy users. No significant cognitive burden was observed while using the scaffolded writing tools, but a moderate decrease in text ownership and satisfaction was noted. Our results have broad implications for the design of AI-powered writing tools, including the need for personalized scaffolding mechanisms.

著者
Paramveer Dhillon
University of Michigan, Ann Arbor, Michigan, United States
Somayeh Molaei
University of Michigan, Ann Arbor, Michigan, United States
Jiaqi Li
Information School, Ann Arbor, Michigan, United States
Maximilian Golub
University of Michigan, Ann Arbor, Michigan, United States
Shaochun Zheng
University of California, San Diego, La Jolla, California, United States
Lionel Peter. Robert
University of Michigan, Ann Arbor, Michigan, United States
論文URL

https://doi.org/10.1145/3613904.3642134

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Writing and AI A

311
4 件の発表
2024-05-16 18:00:00
2024-05-16 19:20:00