LLM responses that are incomplete or incorrect prompt students to question, verify and improve the information, fostering critical thinking through cycles of validation and correction¶

Claim · All claims
Evidence · 1 study · review r2 · q2
Currency · newest study 2025 · checked against its sources 2026-10-19 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Across the reviewed studies, LLMs' imperfect outputs lead students to evaluate accuracy, consistency and trustworthiness of generated content, enhancing critical thinking and mental independence. → Martínez-Peláez 2025

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 synthesis of included studies (RQ1 findings section) reports that imperfect LLM outputs trigger a "cycle of validation and correction, enhancing critical thinking and mental independence"; students learn to evaluate the accuracy and trustworthiness of LLM-generated content. No effect sizes are printed for this synthesis.

"One key educational benefit identified is that LLMs often produce incomplete or incorrect responses, prompting students to question, verify, and improve the information provided"

Discussion¶

Learner Variables¶

• Critical Thinking — outcome: instruction changes it

Related Claims¶

• Meta-reviews reach contradictory conclusions on whether AI reliance harms or helps critical thinking, with substantial design limitations limiting generalizability — the general claim this finding bears on, with the studies behind it
• Working with imperfect AI outputs under mentor supervision was followed by students developing skepticism and independent debugging skills — a narrower finding that bears on this claim
• Students remained cautious about relying on GenAI throughout the creative process, citing imperfect outputs and perceived loss of ownership — related
• Reviewed literature reports risks of overreliance, AI errors in complex tasks, and students' uncritical acceptance of AI-generated outputs — reports the opposite
• Gen-AI hallucinates sources and values and produces convincing but incorrect explanations, risking student misinformation — related
• Higher-quality prompt engineering skills predict the quality of LLM output in goal-directed use of generative AI tools — related
• Leading LLMs hallucinated legal authorities in 58%-88% of tested cases while failing to recognise incorrect legal assumptions in prompts
• Critical AI literacy emerged as both a learning-design goal and a condition of teachers' professional mediation — related
• Optimizing prompts can vastly improve the accuracy of LLM outputs, but critical evaluation of the resulting outputs still requires domain expertise. — related