面向低连接环境的离线优先LLM架构：用于自适应学习
Arapai: An Offline-First LLM Architecture for Adaptive Learning in Low-Connectivity Environments
AI总结：
本文提出一种离线优先的LLM架构，适用于低连接环境中的自适应学习，通过本地推理和硬件感知模型选择，提供课程对齐的解释和结构化学术支持，适应不同教育阶段的学习者需求。
摘要：
人工智能（AI）和大语言模型（LLMs）通过使对话辅导、个性化解释和探究式学习成为可能，正在改变教育技术。然而，大多数基于AI的学习系统依赖持续的互联网连接和云计算，限制了其在带宽受限环境中的使用。本文提出了一种面向低连接环境的离线优先大语言模型架构，该系统通过量化语言模型在本地进行所有推理，并结合硬件感知的模型选择，使部署在低规格CPU设备上成为可能。通过去除对云基础设施的依赖，该系统通过自然语言交互提供课程对齐的解释和结构化的学术支持。为了支持不同教育阶段的学习者，该系统包括自适应响应级别，生成不同复杂程度的解释：简单英语、初级中学、高级中学和技术。这使解释能够根据学生能力进行调整，提高学术概念的清晰度和理解。该系统在有限连接条件下部署于选定的中学和高等教育机构，并在技术性能、可用性、感知响应质量和教育影响方面进行了评估。结果显示，在传统硬件上稳定运行，响应时间可接受，用户对支持自主学习的支持有积极评价。这些发现证明了在低连接环境中离线大语言模型部署用于AI辅助教育的可行性。
英文摘要：
Artificial intelligence and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalised explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents Arapai, an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aware model selection to enable deployment on low-specification, CPU-only devices. By removing dependence on cloud infrastructure, the system provides curriculum-aligned explanations and structured academic support through natural-language interaction. To support learners at different educational stages, the system includes adaptive response levels that generate explanations at varying levels of complexity: Simple English, Lower Secondary, Upper Secondary, and Technical. The system was evaluated with 120 students and 9 instructors from secondary and tertiary institutions under limited-connectivity conditions. Results indicate stable operation on legacy hardware, acceptable response times of 1-3 seconds for typical queries, and positive user perceptions of its effectiveness in supporting self-directed learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
