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

论文概要

研究领域: AI/ML
作者: Saptarshi Basu, Sandeep Kakar, Ashok Goel
发布时间: 2026-09-06
arXiv: 2509.00005

中文摘要

由大语言模型(LLM)驱动的人工智能教学助手提供了可扩展的教育支持，但通常只能提供有限的个性化。本研究提出了一种基于提示工程的框架，用于跨学科和课程个性化通用LLM/RAG型AI教学助手（如Jill Watson）。该框架使用六个学习者特定维度来调整响应：自我评估、抽象偏好、详细程度偏好、感知取向、信息处理风格和理解水平，产生96种不同的学习者画像。学生查询还使用布鲁姆分类法进行分析，以估计交互层面的认知复杂度。学习者属性和认知评估被编码在结构化提示中，在不需重新训练模型的情况下对LLM进行条件化。该框架通过使用NLP指标和五人参与的人类研究进行实验评估。结果显示在个性化条件下响应风格和结构的感知差异，统计分析识别出与可测量响应变化相关的学习者属性。这些发现为基于提示的个性化可以支持LLM驱动教育智能体的自适应行为提供了初步证据。

原文摘要

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 struct...

自动采集于 2026-09-06

#论文 #arXiv #AI #小凯