Date
Publisher
arXiv
The double-edged sword of integrating Large Language Models (LLMs) requires an effective triadic collaboration mechanism among LLMs, teachers and students, especially for K-12 education. By developing a triadic collaboration system to support K-12 writing learning, a multidimensional evaluation framework grounded in Systemic Functional Linguistics and the suggestion trajectory tracing pipeline, this paper contributes a large-scale empirical dataset involving $57,954$ essays from $10,195$ students across $120$ schools over two years. Our findings confirm the efficacy of this system in improving writing quality through a strategic labor division: the LLM serves as a generative engine to mitigate teacher burnout, and the teacher acts as a pedagogical gatekeeper and bridge to guarantee feedback quality. While both LLM and teacher are critical for skill improvement, we uncover a ceiling effect where excessive linguistic expansion yields diminishing marginal utility. These suggest a dynamically adaptive LLM-teacher collaboration as student proficiency increases.
Study at a glance
- Question: How does three-way collaboration between students, AI, and teachers impact student writing quality and revision?
- Setting and data: 10,195 students across 120 schools, analyzing 57,954 essays from 1,602 writing tasks between May 2023 and July 2025.
- Method: Fixed effects regression and linguistic text analysis of student essay revisions before and after feedback.
Why it matters
Most studies on AI-assisted writing focus on adults in lab settings, leaving unresolved whether and how AI and teachers can collaborate effectively to support K-12 writing without homogenizing student expression or reducing student ownership.
Key findings
- Students improved their writing quality by over 5%, with teacher grades increasing by 5.17 points and AI grades rising by 5.01 points across revisions.
- Teachers adopted a gatekeeper role that cut workload nearly 40-fold, while students adopted teacher-refined feedback at higher rates than raw AI suggestions.
- Linguistic expansion benefited lower-performing students, but higher-performing students faced a ceiling effect where further complexity yielded diminishing or even negative returns.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Why use AI?
Study design
