用小模型生成可控难度与安全的儿童英语阅读故事
Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety
- 用8B参数小模型微调，实现对阅读难度和错误模式的精准控制
- 微调后的故事在难度指标上优于零样本GPT-4o和70B大模型
- 适合教师、家长在课堂或家庭中生成安全有趣的英语读物
大型语言模型广泛应用于教育场景，如生成儿童读物。但生成内容常超出儿童阅读能力，且运行成本高。本文基于专家设计的儿童阅读课程及GPT-4o和Llama 3.3 70B生成的故事，对三个8B参数的LLM进行微调实验。结果表明，经适当微调后，8B模型生成的英语读物在难度相关指标上优于零样本的GPT-4o与Llama 3.3 70B，且几乎无安全问题。该方法以可控性优先，使小型经济模型能支持教师、家长和孩子在教室与家庭中生成符合兴趣、难度可控且安全的英语阅读故事。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are widely applied in educational practices, such as for generating children's stories. However, the generated stories are often too difficult for children to read, and the operational cost of LLMs hinders their widespread adoption in educational settings. We used an existing expert-designed children's reading curriculum and its corresponding generated stories from GPT-4o and Llama 3.3 70B to design different experiments for fine-tuning three 8B-parameter LLMs, which then generated new English reading stories that were subjected to quantitative and qualitative evaluation. Our method prioritizes controllability over scale, enabling educators to target reading levels and error patterns with a compact, affordable model. Our evaluation results show that with appropriate fine-tuning designs, children's English reading stories generated by 8B LLMs perform better on difficulty-related metrics than those from zero-shot GPT-4o and Llama 3.3 70B, with almost no discernible safety issues. Such fine-tuned LLMs could be more broadly used by teachers, parents, and children in classrooms and at home to generate engaging English reading stories with children's interests, controllable difficulty and safety.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。