Dataset of 103 postgraduate data-science project proposals with instructor feedback used to evaluate GPT feedback generation¶
Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
A dataset created by Wei Dai et al. containing 103 anonymised postgraduate data-science project proposals and associated instructor feedback scored across five rubric aspects for evaluating GPT-generated feedback.
Components¶
Claims¶
- Feedback generated by GPT-3.5 and GPT-4 was significantly more readable than instructor-generated feedback on open-ended writing tasks [+M]
- GPT-4 outperformed GPT-3.5 and human instructors in producing feedback containing effective feedback components such as feeding-up and process-level information [+M]
Related Products and Programmes¶
-
Key Sources¶
- Wei Dai, Yi-Shan Tsai, Jionghao Lin, Ahmad Aldino, Hua Jin, Tongguang Li, Dragan Gašević, Guanliang Chen. (2023). Assessing the Proficiency of Large Language Models in Automatic Feedback Generation: An Evaluation Study. Preprint submitted to Elsevier. https://scholar.google.com/scholar?q=Assessing+the+Proficiency+of+Large+Language+Models+in+Automatic+Feedback+Generation
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
dataset-of-103-postgraduate-data-science-project-proposals-with-instructor-feedback-used-t |
title |
Dataset of 103 postgraduate data-science project proposals with instructor feedback used to evaluate GPT feedback generation |
description |
A dataset created by Wei Dai et al. |
status |
review |
product_kind |
dataset |
generated |
by process:settle-candidates on 2026-10-15 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.