Randomized experiment finds AI draft assistance raises feedback provision by teaching assistants 10.8 percentage points without harming quality.
arXiv preprint arXiv:2410.03017 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
CourseBlueprint builds a typed pipeline over a 23-lecture biomedical imaging corpus to generate prerequisite-aware, learner-adaptive videos with auditable engagement contracts and slide grounding.
AI alignment must move beyond assuming users have fully formed goals and instead provide active cognitive support to help form and refine intent over time.
Two controlled experiments show multi-agent LLM configurations with both tutors and peers deliver higher learning gains and less homogeneous outputs than single-LLM tutoring in math problem-solving and essay writing.
AI scoring of training and real-life transcripts from 86 tutors shows training performance predicts real tutoring quality with 0.25 SD effect size using mixed-effects models.
citing papers explorer
-
AI Assistance for Discretionary Work: Increasing Feedback Provision in Higher Education
Randomized experiment finds AI draft assistance raises feedback provision by teaching assistants 10.8 percentage points without harming quality.