Teacher and student feedback indicates LLM-based formative assessment can reduce grading burden, surface misconceptions, and build student trust without replacing teacher judgment¶

Claim · All claims
Evidence · 1 study · qualitative r? · q1
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q1 i? The authors report that teacher feedback suggests LLM-based formative assessment can reduce grading burden, surface student misconceptions, and support targeted instructional intervention without replacing teacher judgment, and that explanatory AI scoring can build student trust. → Cohn 2026

Evidence¶

Cohn 2026¶

Cohn, C., Ashwin T S, Mohammed, N., & Biswas, G. (2026). CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedback. arXiv preprint. https://arxiv.org/abs/2504.02323 doi:10.48550/arxiv.2504.02323

q1 · i? · qualitative · r?

The article's own summary of its RQ2 qualitative findings, drawn from semi-structured interviews with two teachers and a survey/focus group with 23 students reviewing AI-scored Science Concepts and Reasoning responses. The description reflects the authors' stated summary; the detailed results section was not available in the supplied text.

"Teacher feedback suggests LLM-based formative assessment can reduce grading burden, surface student misconceptions, and support more targeted instructional intervention without replacing teacher judgment."

Discussion¶

Related Claims¶

• Effective implementation of formative assessment is hindered by its complexity, summative-assessment pressure, and teachers' negative early experiences — the general claim this finding bears on, with the studies behind it
• Reviewed literature reports risks of overreliance, AI errors in complex tasks, and students' uncritical acceptance of AI-generated outputs — related
• Trustworthiness metrics and visualizations surfaced previously overlooked pedagogical risks and enabled more deliberate reasoning about trade-offs between competing objectives — related
• LLM-based assessment can replace similarity-based methods because it needs no ground-truth response and no correctness threshold — related
• Immersive learning tools should surface misconceptions and track learner difficulties so instructors can adapt teaching and assessment — a broader claim this one bears on
• The taxonomy decodes overlapping misconceptions behind a single observed loop-tracing error — related
• Pedagogically scaffolded generative AI in design thinking education augments rather than replaces human judgment — related