发表机构
Texas A&M University–Corpus Christi; University of Missouri; University of California, Riverside; University of South Florida（德克萨斯A&M大学科珀斯克里斯蒂分校; 密苏里大学; 加利福尼亚大学河滨分校; 南佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对语言学习资源因成本受限的问题，提出LLMersion框架，利用小型开放权重模型在本地笔记本电脑上实现完整四技能训练，成本极低，并发布开源原型以促进教育公平。
AI 中文摘要
人工智能在教育领域最能发挥作用之处，正是那些因成本而被限量供应的基本条件。对于语言学习者而言，这一条件便是教师的声音，它将听、说、读、写融为一体。已发表的证据表明，为何大多数学习者缺乏这一条件：从全球4400万教师的短缺，到沉重的家庭辅导费用；也说明了为何技术未能替代它：计算机辅助语言学习虽被证明有效但范围狭窄，应用程序预设了26亿人缺乏的互联网连接，而“每个儿童一台笔记本电脑”项目的随机评估发现，没有强大软件的硬件教不了任何东西。我们提炼出八项困难与四项约束条件，并论证小型开放权重模型能消除最后一项约束：完整的四项技能栈如今可装入价值200美元级别的笔记本电脑，并且根据社区测量，其生成速度与语音消耗速度相当，每学习小时的电费约为1美分。因此，我们提出LLMersion——一种完全在家庭运行、基于学习者自身文档、代码库由AI编写、AI理解且AI更新、任何人都可定制的AI教育方案；并发布LLMersion-1，一个已开源的原型（见本URL），同时展望了私人学习智能体的愿景。
英文摘要
Artificial intelligence helps education most where an essential provision has been rationed by cost. For language learners that provision is a teacher's voice, which binds listening, reading, speaking, and writing into one act. Published evidence shows why most learners lack it, from a global shortage of 44 million teachers to heavy household tutoring bills, and why technology has not substituted for it: computer-assisted language learning proved effective but narrow, applications presuppose connectivity 2.6 billion people lack, and One Laptop per Child's randomized evaluation found that hardware without capable software teaches nothing. We distill eight difficulties and four binding constraints, and argue that small open-weight models dissolve the last: a complete four-skill stack now fits a \$200-class laptop and, on community measurements, generates at the pace speech is consumed, for about one US cent of electricity per study hour. We therefore propose LLMersion, a scheme for AI for education that runs entirely at home, over the learner's own documents, with an AI-written, AI-understood, AI-updated codebase anyone can customize; present LLMersion-1, a released open-source prototype (https://github.com/QM378/LLMersion ); and outline the vision of a private learning agent.
Comments24 pages, 5 figures, 7 tables. v2 adds interface figures and the companion tool LLMersion Narrator. Code: https://github.com/QM378/LLMersion ; Narrator: https://github.com/QM378/llmersion-narrator
