用AI打造地质论文对话系统，精准回答高校师生问题
Geolog-IA: Conversational System for Academic Theses
- 融合Llama 3.1与Gemini 2.5，结合RAG和SQLite防幻觉
- BLEU得分0.87，生成答案高度一致准确
- 适合高校师生在地质研究中快速查资料
本文介绍Geolog-IA的开发，这是一个基于人工智能的对话系统，可自然回应厄瓜多尔中央大学地质学论文相关问题。系统采用Llama 3.1和Gemini 2.5语言模型，结合检索增强生成（RAG）架构与SQLite数据库，有效缓解幻觉和知识过时问题。通过BLEU指标评估，系统平均得分为0.87，表明生成回复具有高一致性与准确性。该系统提供直观的网页界面，便于导师、教师、学生及行政人员交互与信息获取，有望在教育、培训与科研中发挥关键支持作用，并为其他学科应用奠定基础。
原文摘要 · Abstract (English)
This study presents the development of Geolog-IA, a novel conversational system based on artificial intelligence that responds naturally to questions about geology theses from the Central University of Ecuador. Our proposal uses the Llama 3.1 and Gemini 2.5 language models, which are complemented by a Retrieval Augmented Generation (RAG) architecture and an SQLite database. This strategy allows us to overcome problems such as hallucinations and outdated knowledge. The evaluation of Geolog-IA's performance with the BLEU metric reaches an average of 0.87, indicating high consistency and accuracy in the responses generated. The system offers an intuitive, web-based interface that facilitates interaction and information retrieval for directors, teachers, students, and administrative staff at the institution. This tool can be a key support in education, training, and research and establishes a basis for future applications in other disciplines.
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。