In blind pairwise comparisons, educators rated an LLM tutor (MWPTutor) as better than human tutors from MathDial on empathy, scaffolding, and conciseness, with no significant advantage on engagement.
Digital education council global ai student survey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.ET 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Educators' Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting
In blind pairwise comparisons, educators rated an LLM tutor (MWPTutor) as better than human tutors from MathDial on empathy, scaffolding, and conciseness, with no significant advantage on engagement.