A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant

一种用于在通用人工智能助教中开发可扩展、灵活且实时混合微观个性化的提示工程方法

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.

摘要： 由大语言模型（LLM）驱动的人工智能（AI）助教提供了可扩展的教育支持，但往往缺乏个性化。本研究提出了一种基于提示工程的框架，用于对诸如 Jill Watson 等基于 LLM/RAG 的通用 AI 助教进行跨学科和跨课程的个性化定制。

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.

该框架通过六个学习者特定维度来调整回复：自我评估、抽象偏好、冗长偏好、感知导向、信息处理风格以及理解水平，从而生成 96 种不同的学习者画像。此外，学生的问题还会通过布鲁姆分类法（Bloom’s Taxonomy）进行分析，以评估交互层面的认知复杂度。

Learner attributes and cognitive assessments are encoded in structured prompts that condition the LLM without requiring model retraining. The framework is evaluated through experiments using NLP metrics and a human study with five participants.

学习者属性和认知评估被编码在结构化提示中，从而在无需重新训练模型的情况下对 LLM 进行调节。该框架通过使用自然语言处理（NLP）指标的实验以及一项包含五名参与者的人类研究进行了评估。

Results show perceived differences in response style and structure across personalization conditions, with statistical analyses identifying learner attributes associated with measurable response changes. These findings provide preliminary evidence that prompt-based personalization can support adaptive behavior in LLM-powered educational agents.

结果显示，在不同的个性化条件下，回复的风格和结构存在可感知的差异，统计分析识别出了与可测量回复变化相关的学习者属性。这些发现提供了初步证据，表明基于提示的个性化可以支持 LLM 驱动的教育代理实现自适应行为。