First-year EAP students prefer a hybrid feedback model combining AI-generated comments with instructor feedback over either source alone¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2026 · checked against its sources 2026-10-15 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Student responses indicated a clear preference for a hybrid feedback model combining the immediacy of AI-generated comments with the depth and pedagogical value of instructor feedback. → Reza Farzi 2026

Evidence¶

Reza Farzi 2026¶

Reza Farzi. (2026). Human–AI Collaboration in Academic Writing Instruction: Calibrated Feedback Model for EAP. OLBI Journal. https://doi.org/10.18192/olbij.v15i1.7773

q2 · i? · associational · r1

Perception data from the mixed-methods study of 30 first-year EAP students, analyzed as part of the comparison of instructor and ChatGPT-3.5 feedback on their essays. The article reports a "clear preference for a hybrid feedback model"; no effect size is printed.

"Student responses indicated a clear preference for a hybrid feedback model, which combines the immediacy of AI-generated comments with the depth and pedagogical value of instructor feedback."

Discussion¶

Related Claims¶

• After PAIRR, most students prefer combined peer and AI feedback over either source alone — possibly the same claim (merge candidate)
• Students bound their reliance on AI feedback and advocate a hybrid model assigning AI broad language concerns and instructors individualized relational guidance — possibly the same claim (merge candidate)
• EFL students perceive AI-generated writing feedback as a competent source that improves vocabulary, grammar, structure, coherence, and values its immediacy — related
• Business Writing students valued AI feedback for higher-order and sentence-level comments but found it sometimes too general, while appreciating peers' contextual knowledge — related
• Trustworthiness and goodwill, more than expertise, set the limits of students' reliance on AI-generated feedback — related
• GenAI's immediate answers reduce engineering students' teacher-student interactions for generalizable tasks, while teachers remain preferred for complex problem-solving — related
• Students found ChatGPT responses useful but insufficient in depth and detail compared with TA responses — related
• Students perceived peer group feedback as contextually rich but sometimes subjective, and ChatGPT-4o feedback as more objective and well structured but occasionally lacking contextual sensitivity — related
• Human teacher–GenAI collaboration in embodied mathematics learning calls for a complementary interaction model combining AI feedback with human metacognitive guidance — related
• Distance students prefer an institution-embedded assistant offering 24/7 immediate, context-specific feedback over generic content such as ChatGPT — related
• Most students preferred combined peer and AI feedback over either source alone, and rated peer and ChatGPT feedback as similarly useful — related
• Students who preferred AI feedback cited clarity, understandability, consistency, specificity, and 24/7 availability — related
• In a small case study, students given ChatGPT feedback valued its immediacy and alternative analytical perspectives, but one distrusted its answers as 'often made up' for complex data analysis — related
• LLM-generated feedback is more comprehensive in volume than human feedback but is sometimes too generic, abstract, or misaligned with the assigned grade — related
• Students report teacher feedback on writing is insufficient, and they value scores over feedback — related
• ChatGPT-3.5 feedback on EAP argumentative essays aligns closely with human instructor scoring and identifies surface-level issues, but is less effective on rhetorical structure and contextual nuance — related
• Hybrid approaches combining LLMs with traditional knowledge-tracing algorithms outperform either method alone for learner modelling — related