Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale
For K-12 educators and students, this work provides a scalable, evidence-based framework for integrating LLMs into writing instruction, addressing teacher burnout and feedback quality.
The paper presents a triadic LLM-teacher collaboration system for K-12 writing, evaluated on a large-scale dataset (57,954 essays, 10,195 students, 120 schools over two years). The system improves writing quality by dividing labor: LLM generates feedback to reduce teacher burnout, while teachers ensure quality, but excessive linguistic expansion shows diminishing returns.
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.