arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.02653cs.AIcs.IR
收藏

Geolog-IA:面向学术论文的对话系统

Geolog-IA: Conversational System for Academic Theses

Micaela Fuel Pozo, Andrea Guatumillo Saltos, Yeseña Tipan Llumiquinga, Kelly Lascano Aguirre, Marilyn Castillo Jara, Christian Mejia-Escobar

AI总结:

本研究开发了面向厄瓜多尔中央大学地质学论文的AI对话系统Geolog-IA,结合大模型与RAG架构等解决幻觉等问题,BLEU得分达0.87,可为校内多类人员提供信息检索支持,并为跨学科应用奠基。

摘要:

本研究介绍了Geolog-IA的开发情况,这是一款基于人工智能的新型对话系统,可针对厄瓜多尔中央大学的地质学论文问题给出自然回答。我们的方案采用Llama 3.1与Gemini 2.5语言模型,并搭配检索增强生成(Retrieval Augmented Generation, RAG)架构与SQLite数据库,以此解决幻觉、知识过时等问题。使用BLEU指标评估Geolog-IA的性能,平均得分达0.87,表明其生成的回答具备高一致性与准确性。该系统提供直观的网页端界面,方便该校的导师、教师、学生及行政人员交互与检索信息。这款工具可成为教育、培训与研究领域的重要支撑,也为未来在其他学科的应用奠定了基础。

英文摘要:

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 This strategy allows us to overcome problems such as hallucinations and outdated knowledge.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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑