mlsanityData to 14 Oct 2026

Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing

arXiv 2609.25303 ↗First posted 21 Sep 2026cs.AI stat.COcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 32 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

12 of 32 references.

References · 12

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  3. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
  4. 2025In-depth Analysis of Graph-based RAG in a Unified Frameworkcited by 46
  5. 2024WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipediacited by 44
  6. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  7. 2025A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challengescited by 17
  8. 2025Knowledge Graph-extended Retrieval Augmented Generation for Question Answeringcited by 14
  9. 2025Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domainscited by 1
  10. 2025Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Studycited by 1
  11. 2025SocraticAI: Transforming LLMs into Guided CS Tutors Through Scaffolded Interactioncited by 1
  12. 2026Rethinking Scaffolding in LLM Tutors: The Interactional Mismatch Between Benchmarks and Real-World Deploymentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024From Interests to Insights: An LLM Approach to Course Recommendations Using Natural Language Queries
  2. 2026To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval
  3. 2025Reusing Pre-Training Data at Test Time is a Compute Multiplier
  4. 2025From Slides to Chatbots: Enhancing Large Language Models with University Course Materials
  5. 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing
  6. 2024Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
  7. 2025Post-training an LLM for RAG? Train on Self-Generated Demonstrations
  8. 2025Machine Assistant with Reliable Knowledge: Enhancing Student Learning via RAG-based Retrieval