Gurukul AI：面向印度教育体系的交互式AI驱动教育平台

中文摘要 AI 辅助

近期ChatGPT、LLaMA等大语言模型（LLMs）的进展推动了AI驱动教育的变革，但这类系统主要基于以西方为中心的数据训练，不适配印度等地区的课程体系。印度教育体系具有语言多样化、应试导向、围绕标准化教学大纲构建的特点，现有数据集或工具均未覆盖这些特征。本研究基于NCERT（国家教育研究与培训委员会）9-12年级教材，整理了与教学大纲对齐的问答数据集，涵盖印度课程的内容、语境及教学风格。最终数据集包含5个学科的18720组问答对，已公开于此https URL。我们使用该数据集对LLaMA 3.1 8B模型进行微调，并将其部署在适配教育需求的检索增强生成（RAG）框架中。我们推出了GurukulAI，这是一个开放获取平台，支持印度学生与模型对话、解答疑问、练习考试风格的题目、获取语境化答案，并可使用英语和印地语交互。本研究通过将AI本地化适配印度课堂，缩小了全球大语言模型能力与地区教育需求之间的差距，代码已公开于此https URL。

英文摘要

Recent advances in large language models (LLMs) like ChatGPT and LLaMA have transformed AI-driven education, but these systems are predominantly trained on Western-centric data, making them ill-suited for regional curricula like India's. The Indian education system is linguistically diverse, exam-oriented, and structured around standardized syllabi, not addressed by existing datasets or tools. In this work, we curate a syllabus-aligned QA dataset based on NCERT (National Council of Educational Research and Training) textbooks for classes 9-12, capturing the content, context, and teaching style of Indian curricula. The final dataset, comprising 18,720 question-answer pairs across five subjects, is publicly available at https://huggingface.co/datasets/LingoIITGN/Gurukul. We fine-tune the LLaMA 3.1 8B model using this dataset and deploy it in a Retrieval-Augmented Generation (RAG) framework tailored to educational needs. We introduce GurukulAI, an open-access platform that enables Indian students to chat with the model, get doubts cleared, practice exam-style questions, receive contextual answers, and interact in both English and Hindi. By localizing AI for Indian classrooms, our work bridges the gap between global LLM capabilities and regional educational demands. The code is available at https://github.com/lingo-iitgn/GurukulAI.

发表机构

• Indian Institute of Technology Gandhinagar（印度甘地讷格尔印度理工学院）
• Pandit Deendayal Energy University（潘迪特·迪恩代亚尔能源大学）

机构由 AI 辅助整理，请以论文原文为准。