Prompt Engineering for Real-Time Micro-Level Personalization in an LLM-Based AI Teaching Assistant

Forum topic · 小凯 · 2026-09-06

Summary

AI teaching assistants powered by large language models (LLMs) offer scalable educational support but often provide limited personalization. This paper presents a prompt-engineering-based framework for personalizing general-purpose LLM/RAG-based AI teaching assistants, such as Jill Watson, across academic disciplines and courses. The framework adapts responses using six learner-specific dimensions: self-assessment, abstraction preference, verbosity preference, perceptual orientation, information processing style, and level of understanding, yielding 96 distinct learner profiles. Student queries are additionally analyzed using Bloom's Taxonomy to estimate cognitive complexity at the interaction level. Learner attributes and cognitive assessments are encoded in structured prompts, conditioning the LLM without retraining. The framework was evaluated through NLP metrics and a human study with five participants. Results indicate perceived differences in response style and structure under personalization, with statistical analysis identifying learner attributes associated with measurable response changes. The findings offer preliminary evidence that prompt-based personalization can enable adaptive behavior in LLM-driven educational agents. (arXiv: 2509.00005)

Overview

Field: AI/ML Authors: Saptarshi Basu, Sandeep Kakar, Ashok Goel Published: 2026-09-06 arXiv: 2509.00005

Abstract

Artificial intelligence (AI) teaching assistants powered by large language models (LLMs) offer scalable educational support but often provide limited personalization. This study presents a prompt-engineering-based framework for personalizing general-purpose LLM/RAG-based AI teaching assistants such as Jill Watson across academic disciplines and courses.

The framework adapts responses using six learner-specific dimensions: self-assessment, abstraction preference, verbosity preference, perceptual orientation, information processing style, and level of understanding, yielding 96 distinct learner profiles. Student queries are additionally analyzed using Bloom's Taxonomy to estimate cognitive complexity at the interaction level. Learner attributes and cognitive assessments are encoded in structured prompts, conditioning the LLM without retraining.

The framework was evaluated through experiments using NLP metrics and a human study with five participants. Results showed perceived differences in response style and structure under personalized conditions, with statistical analysis identifying learner attributes associated with measurable response changes. These findings provide preliminary evidence that prompt-based personalization can support adaptive behavior in LLM-driven educational agents.

Key Contributions

A prompt-engineering framework for real-time, micro-level personalization of general-purpose AI teaching assistants, requiring no model retraining
Six learner-specific personalization dimensions producing 96 distinct learner profiles
Interaction-level cognitive complexity estimation of student queries via Bloom's Taxonomy
Evaluation combining NLP metrics and a human study, linking learner attributes to measurable changes in LLM responses