Apprentice learner models act as a check against expert blind spots because they start without target skills¶

Claim · All claims
Evidence · 1 study · design r2 · q1
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q1 i? Unlike authoring tools that support constructing expert models directly, apprentice learner models act as a check against expert blind spots because they start without any of the target skills and struggle to acquire them if key intermediate steps are missing during training. → Christopher J. MacLellan & Kenneth R. Koedinger 2022

Evidence¶

Christopher J. MacLellan & Kenneth R. Koedinger 2022¶

Christopher J. MacLellan & Kenneth R. Koedinger. (2022). Domain-General Tutor Authoring with Apprentice Learner Models. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-020-00214-2

q1 · i? · design · r2

The authors argue, citing Li et al. (2013) who showed SimStudent skill models align with student data as well as or better than expert-constructed models across three domains, that apprentice learner models provide a mechanism for detecting missing intermediate skills that experts may overlook due to expert blind spots.

"apprentice learner models act as a check against expert blind spots because they start without any of the target skills and they struggle to acquire them if key intermediate steps are missing during training"

Discussion¶

Related Claims¶

• Experts have reduced access to memory traces of their own cognitive processes due to automatization, and large domain knowledge can disadvantage performance on certain tasks — a broader claim this one bears on
• Apprentice learner models are domain-general: they learn expert models across eight tutor domains without specialized domain knowledge — related
• The New Math movement failed because its foundational concepts were designed to highlight the domain's organization with little regard to how it was to be learned or taught — related