Date
Publisher
arXiv
The incorporation of AI into the assessment of physics laboratory reports offers opportunities to support the review of student work and the provision of feedback. This article revisits an experience involving the use of ChatGPT models to analyze laboratory reports and examines the conditions that influence their usefulness in teaching practice. The analysis considers the evolution of AI models, document-processing procedures, and different modes of interaction, with particular attention to the effective availability of evidence contained in student reports. The findings indicate that differences between AI-generated and teacher assessments may be related not only to model capabilities but also to difficulties in retrieving and interpreting equations, graphs, tables, units, and other visual elements. The possibilities of systematic processing of sets of reports and conversational review of cases requiring more focused analysis are also examined. Based on these observations, a working strategy is proposed in which AI serves as a complementary resource for organizing assessment, supporting feedback, and identifying recurring difficulties in student work. The analysis highlights the importance of document-processing conditions and evidence availability, as well as the teacher's role in interpreting AI-generated information and making evaluative and pedagogical decisions.
Study at a glance
- Question: How can AI tools support physics laboratory report assessment, and what conditions influence their usefulness in teaching?
- Setting and data: Student laboratory reports on reaction time and statistics from an Experimental Physics course; sample size and location not stated in the paper.
- Method: Reflective case review and conceptual analysis comparing API batch processing and conversational interaction across model generations.
Why it matters
Using AI to assess physics laboratory reports offers automation and feedback opportunities, but challenges remain around response reliability, teacher responsibility, and how effectively models interpret complex student evidence.
Key findings
- Differences between AI and instructor assessments may stem from difficulties retrieving and interpreting equations, graphs, tables, and units rather than purely reasoning limitations.
- AI-generated scores are not interchangeable with teacher grades, even when models use the exact same rubric criteria as instructors.
- A hybrid approach combining automated API batch processing for initial reviews with conversational interaction for complex cases can help prioritize teacher attention.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
