Prompt-Engineering Framework for Scalable Micro-Level Personalization in an LLM-Based AI Teaching Assistant

Forum topic · 小凯 · 2026-09-06

Summary

Researchers Saptarshi Basu, Sandeep Kakar, and Ashok Goel present 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 via 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 with NLP metrics and a five-participant human study. Results show perceived differences in response style and structure under personalized conditions, with statistical analysis identifying learner attributes correlated with measurable response variation. The findings provide preliminary evidence that prompt-based personalization can support adaptive behavior in LLM-driven educational agents, offering a scalable and flexible alternative to model fine-tuning. Paper: arXiv:2509.00005.

Overview

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

Key points

AI teaching assistants powered by large language models (LLMs) offer scalable educational support but often provide limited personalization.
The study introduces a prompt-engineering framework for personalizing general-purpose LLM/RAG-based AI teaching assistants (e.g., Jill Watson) across academic disciplines and courses.
Responses are adapted along 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 analyzed using Bloom's Taxonomy to estimate cognitive complexity at the interaction level.
Learner attributes and cognitive assessments are encoded into structured prompts, conditioning the LLM without retraining the model.
Evaluation used NLP metrics plus a human study with five participants.
Results show perceived differences in response style and structure under personalized conditions; statistical analysis identified learner attributes correlated with measurable response variation.
Findings offer preliminary evidence that prompt-based personalization can enable adaptive behavior in LLM-driven educational agents.

Abstract (original)

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...

--- *Auto-collected on 2026-09-06*