ENHANCED RETRIEVAL-AUGMENTED GENERATION FOR STUDENT MENTAL HEALTH SUPPORT USING GENERATIVE ARTIFICIAL INTELLIGENCE
DOI:
https://doi.org/10.34218/IJCET_16_01_277Keywords:
Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Student Mental Health Support, Vector Database, AI For Mental Health, Context-Aware AIAbstract
Generative AI, combined with Retrieval-Augmented Generation (RAG), enhances large language models (LLMs) by integrating dynamic information retrieval, significantly improving response accuracy and contextual relevance. This study explores the implementation of Generative AI-powered RAG in student mental health support systems, demonstrating how it mitigates hallucinations, incorporates real-time knowledge updates, and personalizes assistance. The proposed system integrates retrieval and generation components, leveraging vector-based search mechanisms to access domain-specific mental health knowledge. Comparative analysis with traditional LLMs highlights RAG’s superior accuracy, reduced misinformation, and improved response reliability. Experimental evaluation using context precision, hit rate, faithfulness, and user satisfaction metrics validates the system's effectiveness. This research underscores the transformative potential of Generative AI-driven RAG in delivering scalable, evidence-based mental health support for students.
References
Bruckhaus, T. (2024). RAG Does Not Work for Enterprises. https://doi.org/10.48550/arxiv.2406.04369.
Wang, X., Wang, Z., Gao, X., Zhang, F., Wu, Y., Xu, Z., Shi, T., Wang, Z., Li, S., Qian, Q., Yin, R., Lv, C., Zheng, X., & Huang, X. (2024). Searching for Best Practices in Retrieval-Augmented Generation. https://doi.org/10.48550/arxiv.2407.01219.
Rathod, P. (2024). Efficient Usage of RAG Systems in the World of LLMs. institute of electrical electronics engineers. https://doi.org/10.36227/techrxiv.171625877.73379410/v1.
Zeng, S., Zhang, J., He, P., Ren, J., Zheng, T., Lu, H., Xu, H., Liu, H., Xing, Y., & Tang, J. (2024). Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data. https://doi.org/10.48550/arxiv.2406.14773.
Chirkova, N., Rau, D., Déjean, H., Formal, T., Clinchant, S., & Nikoulina, V. (2024). Retrieval-augmented generation in multilingual settings. https://doi.org/10.48550/arxiv.2407.01463
Ren, Y., Jin, R., Zhang, T., & Xiong, D. (2024). Do Large Language Models Mirror Cognitive Language Processing? https://doi.org/10.48550/arxiv.2402.18023.
Tigges-Limmer, K., Brocks, Y., Winkler, Y., Stock Gissendanner, S., Morshuis, M., & Gummert, J. F. (2018). Mental health interventions during ventricular assist device therapy: a scoping review. Interactive CardioVascular and Thoracic Surgery, 27(6), 958–964. https://doi.org/10.1093/icvts/ivy125.
Zeng, S., Zhang, J., He, P., Ren, J., Zheng, T., Lu, H., Xu, H., Liu, H., Xing, Y., & Tang, J. (2024). Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data. https://doi.org/10.48550/arxiv.2406.14773.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Dr. P. Swathi, Dr. P. Jyotsna (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
