Get Started
Home
Topics
Search
Library
Research questionHow can general-purpose LLM teaching assistants personalize explanations across courses without costly retraining?A single teaching assistant may need to vary explanation style and complexity for learners with different preferences and levels of understanding. Personalizing those responses across courses is difficult when retraining the model is costly or inflexible.
AI
AI Agents
Evaluation & Benchmarks
Natural Language Processing
Reasoning
Retrieval-Augmented Generation
Latest papersRecent research connected to this question, newest first.A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching AssistantThe study presents a prompt-engineering framework that conditions responses on six learner dimensions and estimates query complexity using Bloom’s Taxonomy, producing 96 learner profiles. It reports NLP metrics and a human study with five participants using assistants such as Jill Watson; the evidence is preliminary and concerns measurable response-style differences.research paper · Sep 3, 2026
Related questions
How can multi-turn LLM tutors personalize progressive guidance while preserving answer correctness?How can instruction-tuned LLMs learn corpus-specific knowledge without exhaustive synthetic QA or instruction fine-tuning?How can LLM agents generalize to unseen tasks without directly fine-tuning their policies?How can one deployable LLM learn from multiple specialized teachers when the most reliable teacher varies by sample?