AI-Assisted Assessment of Experimental Physics Laboratory Reports: Potential, Limitations, and Support for Teaching Practice
Abstract
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.
Related
- Wigner Time: from experimental intent to real-time laboratory control
- Combining physical models with dynamically acquired experimental information for the optimization of multicomponent NASICON fast ionic conductors in a self-driving laboratory
- Multi-scale assessment of the time-dependent mechanical behavior of perineal tissues via experimental testing and structural analysis
- Agent-assisted experimental strategy transfer across quantum processors
- A Multi-Modal Assessment to Evaluate Changes Following Pediatric Robot-Assisted Gait Training: A Case Study
BibTeX
@misc{abreu2026aiassisted,
title = {{AI-Assisted Assessment of Experimental Physics Laboratory Reports: Potential, Limitations, and Support for Teaching Practice}},
author = {Marcos Abreu and Cecilia Stari and Arturo C. Marti},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22417},
eprint = {2609.22417},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22417},
}
RIS
TY - UNPB
TI - AI-Assisted Assessment of Experimental Physics Laboratory Reports: Potential, Limitations, and Support for Teaching Practice
AU - Marcos Abreu
AU - Cecilia Stari
AU - Arturo C. Marti
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2609.22417
UR - https://arxiv.org/abs/2609.22417
AB - 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.
ER -