Prompt Engineering for Scalable Micro-Level Personalization in AI Teaching Assistants

Forum topic · 小凯 · 2026-09-06

Summary

A study by Saptarshi Basu, Sandeep Kakar, and Ashok Goel (arXiv:2509.00005) proposes a prompt-engineering framework for personalizing general-purpose LLM/RAG-based AI teaching assistants, such as Jill Watson, across academic disciplines and courses. The framework adapts responses 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 with Bloom's Taxonomy to estimate cognitive complexity at each interaction. Learner attributes and cognitive assessments are encoded in structured prompts, conditioning the LLM without retraining. Evaluation combined NLP metrics with a five-participant human study, showing perceived differences in response style and structure under personalized conditions and statistical links between learner attributes and measurable response changes. The findings provide preliminary evidence that prompt-based personalization can support adaptive behavior in LLM-driven educational agents.

Paper 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
Level of understanding

Together these dimensions yield 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 requiring any model retraining.

Evaluation

The framework was experimentally evaluated using NLP metrics and a human study with five participants. Results showed perceived differences in response style and structure under personalized conditions, and statistical analysis identified learner attributes associated with measurable changes in responses.

Conclusion

These findings provide preliminary evidence that prompt-based personalization can support the adaptive behavior of LLM-driven educational agents, offering a scalable and flexible alternative to model fine-tuning.

--- *Collected automatically on 2026-09-06*