Use joint AI processing of report sets to identify recurring difficulties and guide collective feedback and teaching priorities¶

Strategy · All strategies
Evidence · no claims cited

Description¶

Beyond individual review, the article proposes processing sets of reports to identify trends and recurring difficulties across submissions, such as treatment of uncertainties and significant figures, graph interpretation and construction, handling of units, or formulation of conclusions. Results can be organized by rubric criterion to give an overall picture of group difficulties, informing specific activities, reinforcement planning, and collective feedback sessions addressing the most frequent errors instead of repeating explanations individually.

Design Implications¶

Context¶

Requirements¶

• A large number of reports for joint processing; instructor interpretation of identified patterns.

Constraints¶

• Results should be interpreted as supporting information for teaching decisions rather than as an automatic diagnosis of learning.

Target Learners¶

• higher education student groups in laboratory courses

Target Learning Goals¶

• identifying and addressing recurring difficulties in experimental physics skills

Related Strategies¶

• Three-stage hybrid workflow: API batch review, identification of doubtful cases, focused conversational teacher review
• Design rubric criteria and model instructions in observable, verifiable terms with citable evidence requirements
• Mitigate extraction errors by requiring high-resolution PDFs, equation-editor equations, and legible graph axes, units, and legends

Examples¶

-

Key Sources¶

• Marcos Abreu, Cecilia Stari, Arturo C. Martí. (2026). AI-Assisted Assessment of Experimental Physics Laboratory Reports: Potential, Limitations, and Support for Teaching Practice. arXiv. https://arxiv.org/abs/2609.22417