Proposal for an intelligent agent to improve access to information in the university context XI Taller Internacional “La transformación digital y las tecnologías de avanzada en la Educación Superior”
Article Sidebar
Main Article Content
Abstract
The current work presents the proposal for UPR-Chat, an intelligent agent system designed to improve access to university-specific information, addressing the limitations of Large Language Models (LLMs) such as outdated knowledge and hallucinations. Based on GraphRAG technology, UPR-Chat integrates a knowledge graph built with local university data (using tools like Neo4j and LangChain) to provide relevant context to an LLM, enabling the generation of more accurate and contextualized responses. The methodology included a literature review, requirements analysis, and the design of specialized agents (such as "Professor" and "Researcher") with toolsets tailored to teaching and research needs, aiming to offer an efficient and hardware-accessible solution for the university community.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Bach, S. H., Sanh, V., Yong, Z., Webson, A., Colin, R., Nayak, N., Sharma, A., & Taewoon, K. (2022). PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts (arXiv:2202.01279). arXiv. https://doi.org/10.48550/arXiv.2202.01279
Buyl, M., Rogiers, A., Noels, S., Bied, G., Dominguez-Catena, I., Heiter, E., Johary, I., Mara, A., Romero, R., Lijffijt, J., & Bie, T. (2025). Large Language Models Reflect the Ideology of their Creators (arXiv:2410.18417). arXiv. https://doi.org/10.48550/arXiv.2410.18417
Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., & Larson, J. (2024). From Local to Global: A Graph RAG Approach to Query-Focused Summarization (arXiv:2404.16130; Versión 1). arXiv. https://doi.org/10.48550/arXiv.2404.16130
Enzo. (2024, julio 11). The GraphRAG Manifesto: Adding Knowledge to GenAI. Graph Database & Analytics. https://neo4j.com/blog/graphrag-manifesto
Huang, S., Dong, L., Wang, W., Hao, Y., Singhal, S., Ma, S., Lv, T., Cui, L., Mohammed, O., Patra, B., Liu, Q., Aggarwal, K., Chi, Z., Bjorck, J., Chaudhary, V., Som, S., Song, X., & Wei, F. (2023). Language Is Not All You Need: Aligning Perception with Language Models (arXiv:2302.14045). arXiv. https://doi.org/10.48550/arXiv.2302.14045
Olawore, K., McTear, M., & Bi, Y. (2025). Development and Evaluation of a University Chatbot Using Deep Learning: A RAG-Based Approach. Chatbots and Human-Centered AI, 96-111. https://doi.org/10.1007/978-3-031-88045-2_7
Zhao, S., Yang, Y., Wang, Z., He, Z., Qiu, L., & Qiu, L. (2024). Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely (arXiv:2409.14924; Versión 1). arXiv. https://doi.org/10.48550/arXiv.2409.14924
Zhao, W., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, Ch., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., Wen, J. (2023). A Survey of Large Language Models (arXiv:2303.18223; Versión 10). arXiv. https://doi.org/10.48550/arXiv.2303.18223
