Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing
Abstract
Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revised mid-semester. Our prior work built a multimodal retrieval-augmented generation (RAG) system over an authentic machine learning course corpus (Foundations of Machine Learning) and found that retrieval improved contextual grounding, but that fixed retrieval strategies were suboptimal. That motivates a different question: whether how a corpus is structured at ingest time matters more than how much is retrieved at query time. We present a controlled head-to-head comparison of two knowledge representations over an identical classroom corpus: (A) vector RAG, replicating the best-performing configuration from our prior study, and (B) an LLM-compiled wiki (Karpathy framework), in which the corpus is synthesized at ingest into linked concept pages with explicit cross-references and citations back to source materials. We evaluate 59 questions spanning single-fact recall, cross-unit concept linking, synthesis and explanation, and currency after a syllabus revision, scored by an LLM judge against a human-authored rubric. Both representations answered single-fact questions about equally well (9.33 vs. 9.96 of 10), but diverged sharply on questions requiring links across course units. The compiled wiki remained accurate and grounded (9.93; 100% grounded in cited sources), while retrieval scored lower and was markedly less grounded (8.14; 64%). The wiki's citations let students and instructors trace any claim back to the lecture that introduced it, adding a layer of dynamic retrieval that machine learning courses require. While further testing is needed, instructors using AI to support learning in ML courses should consider wiki-based structure for its potential to support foundational elements of best practice.
Related
- Learning to Bias: Machine Learning-Enhanced Particle Filters
- An overview of machine learning-enhanced iterative methods for systems of linear and nonlinear equations
- Machine Learning-Enhanced Tabu Search for Tactical Wireless Network Design
- Deep Learning of Topological Equivalence Classes
- Private online learning and prediction for Littlestone classes
BibTeX
@misc{wright2026potential,
title = {{Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing}},
author = {Brian Wright},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.25303},
eprint = {2609.25303},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.25303},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing
AU - Brian Wright
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.25303
UR - https://arxiv.org/abs/2609.25303
AB - Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revised mid-semester. Our prior work built a multimodal retrieval-augmented generation (RAG) system over an authentic machine learning course corpus (Foundations of Machine Learning) and found that retrieval improved contextual grounding, but that fixed retrieval strategies were suboptimal. That motivates a different question: whether how a corpus is structured at ingest time matters more than how much is retrieved at query time. We present a controlled head-to-head comparison of two knowledge representations over an identical classroom corpus: (A) vector RAG, replicating the best-performing configuration from our prior study, and (B) an LLM-compiled wiki (Karpathy framework), in which the corpus is synthesized at ingest into linked concept pages with explicit cross-references and citations back to source materials. We evaluate 59 questions spanning single-fact recall, cross-unit concept linking, synthesis and explanation, and currency after a syllabus revision, scored by an LLM judge against a human-authored rubric. Both representations answered single-fact questions about equally well (9.33 vs. 9.96 of 10), but diverged sharply on questions requiring links across course units. The compiled wiki remained accurate and grounded (9.93; 100% grounded in cited sources), while retrieval scored lower and was markedly less grounded (8.14; 64%). The wiki's citations let students and instructors trace any claim back to the lecture that introduced it, adding a layer of dynamic retrieval that machine learning courses require. While further testing is needed, instructors using AI to support learning in ML courses should consider wiki-based structure for its potential to support foundational elements of best practice.
ER -