This work presents the design, implementation, and evaluation of a system for generating personalized reading content using Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG). The proposed architecture consists of four modules: Input, RAG, Generation, and Judging and enables users to specify both a question and a target reading content complexity. RAG is employed to retrieve relevant information from the Internet, enriching and grounding the content produced by three modern LLMs: Meta LLaMA 4 Scout, LLaMA 3.1 8B Instant, and Google Gemma2 9B. Reading materials are generated using three prompting strategies (Chain-of-Thought, zero-shot, and few-shot), and the LLM-as-a-Judge module automatically evaluates answer quality and alignment with the desired readability level. Experimental results show that RAG consistently improves system performance across all models and prompting techniques, increasing relevance and particularly groundedness by up to 26-35 percentage points. Overall, the findings demonstrate that the RAG-augmented architecture effectively produces reading content tailored to user queries and desired textual complexity.

翻译：本文介绍了利用大语言模型（LLMs）结合检索增强生成（RAG）技术生成个性化阅读内容的系统设计、实现与评估。所提出的架构包含四个模块：输入模块、RAG模块、生成模块和评判模块，能够使用户同时指定问题及目标阅读内容的复杂度。RAG技术用于从互联网检索相关信息，以丰富和约束由三种现代LLM（Meta LLaMA 4 Scout、LLaMA 3.1 8B Instant和Google Gemma2 9B）生成的内容。阅读材料通过三种提示策略（思维链、零样本和少样本）生成，而LLM作为评判模块则自动评估答案质量及其与预期可读性水平的一致性。实验结果表明，RAG在所有模型和提示技术中均能持续提升系统性能，使相关性和尤其是有据可依性最高提升26-35个百分点。总体而言，研究证明基于RAG增强的架构能有效生成符合用户查询和预期文本复杂度的阅读内容。