Implement an AI-Peer-Teacher hybrid integrated feedback model staged across drafting, revision, and polishing phases¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article proposes a staged hybrid feedback workflow for L2 writing instruction: "during the initial drafting phase, AI provides real-time standardized content logic guidance and basic error marking; in the in-depth revision phase, peer collaboration focuses on deep mutual evaluation and negotiation; and in the final polishing phase, teachers offer 'expert' high-level feedback". The model aims to integrate the breadth of tool-mediated support, the depth of expert guidance, and the extent of social interaction, supporting learners across different levels of ZPDs. It is grounded in the study's finding that the two feedback modes are heterogeneous scaffolds with complementary strengths.

Design Implications¶

Context¶

Requirements¶

• Teachers assume supervisor and supporter roles, including sampling reviews of feedback quality and timely personalized interventions for struggling groups
• Students receive training to improve their intermediary capabilities for effective interaction with AI

Constraints¶

• The article states a single mode cannot comprehensively address the multidimensional challenges of L2 writing ability development, motivating the hybrid design

Target Learners¶

• Second-year English majors in application-oriented universities

Target Learning Goals¶

• L2 argumentative writing quality
• content and organizational development
• syntactic and lexical development

Affordances¶

• Sct Scaffolding Zpd Feedback Account

Related Strategies¶

• Implement AI-peer integrated feedback as a standardized two-phase revision cycle with rubric-aligned prompting and instructor monitoring
• Collaborative Human-AI Revision Design embedding prompt engineering across drafting, feedback, and rewriting phases
• Integrate AI feedback as a supportive resource within process-oriented drafting cycles, with explicit guidance on critical evaluation
• Calibrate GenAI feedback through calibrated prompts and pedagogical (re-)framing
• Ongoing Feedback
• Revision Cycles
• Calibrate AI writing support by providing contextual feedback, dialogic scaffolding, and initiative matched to learner needs and task complexity
• Implement AI-assisted report feedback through a four-stage phased pathway beginning with mature low-level tools
• Have students compare their peer-feedback revisions with AI-generated revisions to examine dialogic positioning

Examples¶

-

Key Sources¶

• Tang J, Li P, Luo R (2026) Teacher feedback VS AI-assisted peer feedback in L2 writing: A quasi-experimental study in a Chinese University. PLoS One 21(6): e0345976. https://doi.org/10.1371/journal.pone.0345976