MétaCan
Menu
Back to cohort

Building Trust in Educational AI: Designing Effective Human-AI Interfaces for Students and Instructors

2025· article· W7130598143 on OpenAlexaff
Kevin Wang, Bridgette Hunt, Adam Fipke, Ramon Lawrence

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicIntelligent Tutoring Systems and Adaptive Learning
Canadian institutionsUniversity of British Columbia, Okanagan CampusKelowna General Hospital
Fundersnot available
KeywordsAsynchronous communicationWorkflowSoftware deploymentTrustworthinessCognitionCognitive load

Abstract

fetched live from OpenAlex

Integrating artificial intelligence (AI) in education presents unique challenges in balancing automated assistance with the need for trustworthy and personalized student support. Existing AI-driven learning tools often struggle with accuracy, fostering student mistrust, and creating additional oversight demands on instructors. To address these challenges, we present Anytime Question Hub, a system designed to provide students with immediate AI-generated answers to asynchronous questions while incorporating human-in-the-loop workflows for instructor oversight. The platform ensures all queries are resolved through a combination of AI responses and instructor verification, offering tools that minimize cognitive and administrative burden for educators. Deployment in a computer science course with 225 students highlights its potential to enhance student engagement and trust while reducing repetitive communication tasks for faculty. Our findings underscore the importance of integrating transparent, non-intrusive human-AI collaboration to support robust and reliable automated assistance in educational settings.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.007
metaresearch head score (Gemma)0.055
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.039

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.055
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0020.002
Scholarly communication0.0050.009
Open science0.0020.007
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0040.002

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.

Opus teacher head0.023
GPT teacher head0.373
Teacher spread0.350 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicIntelligent Tutoring Systems and Adaptive LearningFrench-language works237,207