Expert rubric ratings overstate student-perceived helpfulness of AI-generated hints in 26.6% of cases, with mismatch reasons grouped into five categories and preliminary fixes proposed.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bridging Gaps Between Student and Expert Evaluations of AI-Generated Programming Hints
Expert rubric ratings overstate student-perceived helpfulness of AI-generated hints in 26.6% of cases, with mismatch reasons grouped into five categories and preliminary fixes proposed.