MétaCan
Menu
Back to cohort

Enhancing Contextual Understanding in AI-Powered Tutoring: Evaluating the Oliver System for Effective Learning Support

2025· article· en· W4409992471 on OpenAlexaff
Haoran Zhu, Michael Cooper-Stachowsky, Zille Huma Kamal

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicIntelligent Tutoring Systems and Adaptive Learning
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsComputer scienceArtificial intelligenceMachine learningHuman–computer interaction

Abstract

fetched live from OpenAlex

In recent years, advancements in conversational AI have led to the development of intelligent tutoring systems to enhance learning experiences through interactive conversation. This paper presents Oliver, an innovative virtual teaching assistant and course management system that leverages contextual memory and response strategies designed to promote active learning and critical thinking. Unlike traditional models that frequently offer direct answers, Oliver encourages exploration and comprehension. We also evaluated Oliver against ChatGPT-4o mini in a controlled environment with over 100 real class interactions by using Bloom's Taxonomy as a framework. Results indicate that Oliver retains lecture-related context and promotes learning more effectively, with 90% of responses fostering higher-order thinking and critical engagement, compared to 60% from ChatGPT-4o mini. These findings underscore Oliver's potential to serve as a powerful tool in education, supporting learners in developing deeper cognitive skills rather than relying on rote memorization.

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)0.002
metaresearch head score (Gemma)0.011
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.002
Threshold uncertainty score0.011

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.011
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0020.000

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 head0.049
GPT teacher head0.335
Teacher spread0.285 · 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 designNot applicable
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