LLMs can deliver scalable, personalized, interactive feedback almost instantly, reducing dependency on teacher availability and supporting self-regulated learning in large courses¶

Claim · All claims
Evidence · 1 study (2 entries) · review r2 · q2
Currency · newest study 2025 · checked against its sources 2026-10-20 (automated, 2 of 2 entries) · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly

Subclaims¶

q2 i? The reviewed studies show LLMs respond to student questions almost instantly, shortening feedback delay and letting students clarify doubts in real time and take ownership of identifying errors independently. → Martínez-Peláez 2025 q2 i? LLMs can reduce faculty teaching workload by automating feedback on routine tasks such as drafts, quizzes or structured assignments, freeing teachers for tasks needing human expertise. → Martínez-Peláez 2025 (2)

Evidence¶

Martínez-Peláez 2025¶

Martínez-Peláez, R.; Mena, L.J.; Toral-Cruz, H.; Ochoa-Brust, A.; Potes, A.G.; Flores, V.; Ostos, R.; Ramírez Pacheco, J.C.; Félix, R.A.; Félix, V.G. (2025). Can Large Language Models Foster Critical Thinking, Teamwork, and Problem-Solving Skills in Higher Education?: A Literature Review. Systems 2025, 13, 1013. https://doi.org/10.3390/systems13111013

q2 · i? · review · r2

The review's RQ3 synthesis reports students can access LLMs from anywhere at any time, and that LLMs enhance self-regulated learning by enabling students to generate practice tests or self-assessment exercises to monitor progress. No effect sizes are printed.

"Evidence shows that LLMs can respond to student questions almost instantly, thus shortening the delay and reducing dependency on teachers' availability"

Martínez-Peláez 2025 (2)¶

Martínez-Peláez, R.; Mena, L.J.; Toral-Cruz, H.; Ochoa-Brust, A.; Potes, A.G.; Flores, V.; Ostos, R.; Ramírez Pacheco, J.C.; Félix, R.A.; Félix, V.G. (2025). Can Large Language Models Foster Critical Thinking, Teamwork, and Problem-Solving Skills in Higher Education?: A Literature Review. Systems 2025, 13, 1013. https://doi.org/10.3390/systems13111013

q2 · i? · review · r2

Faculty-perspective synthesis in the RQ3 section: automation of routine feedback enables teachers to focus on "complex, high-level tasks that need human expertise and disciplinary judgment", and LLMs can support course design by reviewing assessment items. No effect sizes are printed.

"the reviewed studies emphasize that LLMs can significantly reduce teaching workload by automating feedback on routine tasks such as drafts, quizzes, or structured assignments."

Discussion¶

Related Claims¶

• Human scoring and feedback for HDR takes about 11 minutes 30 seconds per learner, while GPT-based scoring and feedback is nearly instant — a narrower finding that bears on this claim
• Self-regulated learning improves achievement — a broader claim this one bears on
• Self Assessment Improves Self Regulated Learning — related
• Reviewed literature identifies personalisation, adaptive support, rapid feedback, and teacher-facing automation as recurring pedagogical opportunities of AI in mathematics education — possibly the same claim (merge candidate)
• Metacognitive self-regulation mediates the relationships between all three AI interaction mechanisms and both higher-order outcomes — related
• AI scaffolding differs from human scaffolding in availability, feedback timing, and dynamic adjustment, making its developmental impact conditional — related
• Frequent generative AI use for essay writing can foster metacognitive laziness, reducing intrinsic motivation and learning autonomy — reports the opposite
• Evidence suggests over-reliance on generative AI may negatively affect students' self-regulated learning behaviors, potentially harming retention and transfer to novel contexts — reports the opposite
• Feedback Most Effective At Task And Process Levels — related
• GenAI is reshaping assessment practices in computer science education through automation, scalability, and personalized feedback — a broader claim this one bears on
• Automated real-time feedback in an adaptive diagnostic ITS produced greater progression on a SOLO-based mathematics assessment than the same system without real-time feedback — a narrower finding that bears on this claim