Exploring the Impact of Different Assistance Approaches on Students’ Performance in Engineering Lab Courses
Bibliographic record
Abstract
The rise of large language models (LLMs) offers new forms of academic support for STEM students engaged in self-directed study. This study evaluates the impacts of multiple assistance approaches on laboratory course performance, focusing on engineering students in electronics-related disciplines. A cohort of 218 students underwent a redesigned lab course, and their outcomes were compared to those of 177 students from earlier years who did not receive such support. Specifically, we implemented five types of support approaches for students completing laboratory coursework: (1) Teaching Assistant (TA) only, (2) Generic-LLM-only model, (3) Expert-tuned-LLM-only model, (4) TA + Generic LLM model, and (5) TA + Expert-tuned LLM model. Our key findings are as follows: I. Compared to the historical baseline with no support, students assisted by the generic-LLM-only model did not show a significant improvement in performance. II. Teaching assistant involvement was associated with marked improvements in student outcomes, and performance across all TA-involved approaches showed little variation. III. The expert-tuned LLM was more effective than the generic LLM in improving student outcomes. IV. The combined TA + LLM configurations enhanced learning efficiency overall, although they required greater time investment in the early stages of the course. These results highlight the promising role of LLM technologies in the future of engineering education, while also underscoring the continued importance of domain-specific expertise in delivering effective learning support.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".