RAG-Guardrails Integration for AI Content Control
DOI:
Abstract
Generative AI is particularly Large Language Models (LLMs), has shown remarkable potential across domains such as healthcare, legal services, and finance. However, their adoption is hindered by two persistent challenges: hallucination, where models generate factually incorrect information and the risk of producing biased or unsafe content. This paper proposes a hybrid framework that integrates Retrieval-Augmented Generation (RAG) with NVIDIA NeMo Guardrails to address these concerns. RAG mitigates hallucinations by grounding model outputs in externally retrieved, trusted data sources, while NeMo Guardrails enforce domain-specific safety and compliance constraints through predefined behavioral policies. Empirical evaluations demonstrate that this combined approach reduces hallucinated content by 30–45% and improves safety and policy adherence across multiple enterprise use cases. The system exhibits strong potential for deployment in regulated, high-stakes environments. Future work will focus on enhancing real-time responsiveness and expanding multilingual and culturally adaptive capabilities. The proposed framework offers a scalable foundation for building trustworthy, domain-aligned generative AI solutions.
Downloads
Views : 284
Downloads : 457
References
J. Li, K. Larsen, and A. Abbasi, “TheoryOn: A design framework and system for unlocking behavioral knowledge through ontology learning,” MIS Quarterly, vol. 44, no. 4, 2020.
T. Kocmi and C. Federmann, “GEMBA-MQM: Detecting translation quality error spans with GPT-4,” in Proc. Eighth Conf. on Machine Translation, P. Koehn, B. Haddow, T. Kocmi, and C. Monz, Eds., Singapore: Association for Computational Linguistics, pp. 768–775, 2023.
Y. Zhao, “Artificial intelligence and education: End the grammar of schooling,” ECNU Review of Education, vol. 8, no. 1, pp. 3–20, 2024.
L. Floridi and M. Chiratti, “GPT-3: Its nature, scope, limits, and consequences,” Minds and Machines, vol. 30, pp. 681–694, 2020.
T. Crick, “COVID-19 and digital education: A catalyst for change?,” ITNOW, vol. 63, no. 1, pp. 16–17, 2021.
J.-C. Bélisle-Pipon, “Why we need to be careful with LLMs in medicine,” Frontiers in Medicine, vol. 11, Art. no. 1495582, 2024.
S. Dattathrani and R. De, “The concept of agency in the era of artificial intelligence: Dimensions and degrees,” Information Systems Frontiers, pp. 1–26, 2022.
J. L. Cross, M. A. Choma, and J. A. Onofrey, “Bias in medical AI: Implications for clinical decision-making,” PLOS Digital Health, vol. 3, no. 11, Art. no. e0000651, 2024.
J. Hastings, “Preventing harm from non-conscious bias in medical generative AI,” The Lancet Digital Health, vol. 6, no. 1, pp. e2–e3, 2024.
G. Agrawal, T. Kumarage, Z. Arhon, and H. Liu, “Can knowledge graphs reduce hallucinations in LLMs? A survey,” in Proc. Conf. on Can Knowledge Graphs Reduce Hallucinations in LLMs, Mexico City, 2024.
S. Konakanchi, “Next-generation low-latency architectures for real-time AI-driven cloud services,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 10, no. 6, pp. 2307–2318, 2024.
C. Collins, D. Dennehy, K. Conboy, and P. Mikalef, “Artificial intelligence in information systems research: A systematic literature review and research agenda,” International Journal of Information Management, vol. 60, Art. no. 102383, 2021.
S. M. Williamson and V. Prybutok, “The era of artificial intelligence deception: Unraveling the complexities of false realities and emerging threats of misinformation,” Information, vol. 15, Art. no. 299, 2024.
A. Kumah, “Poor quality care in healthcare settings: an overlooked epidemic,” Front. Public Health, vol. 13, p. 1504172, Jan. 2025.
E. Baccour, A. Erbad, A. Mohamed, M. Hamdi, and M. Guizani, “Reinforcement learning-based dynamic pruning for distributed inference via explainable AI in healthcare IoT systems,” Future Gener. Comput. Syst., vol. 155, pp. 1–17, Jun. 2024.
S. Abaimov, “Understanding and classifying permanent denial-of-service attacks,” J. Cybersecur. Priv., vol. 4, pp. 324–339, 2024.
J. A. Yaacoub, O. Salman, H. N. Noura, N. Kaaniche, A. Chehab, and M. Malli, “Cyber-physical systems security: Limitations, issues and future trends,” Microprocess. Microsyst., vol. 77, p. 103201, 2020.
K. M. Miller, K. Lukic, and B. Skiera, “The impact of the General Data Protection Regulation (GDPR) on online tracking,” Int. J. Res. Mark., in press, Mar. 2025.
A. K. Conduah, S. Ofoe, and D. Siaw-Marfo, “Data privacy in healthcare: Global challenges and solutions,” Digit. Health, vol. 11, Jun. 2025.
L. M. Amugongo, P. Mascheroni, S. Brooks, S. Doering, and J. Seidel, “Retrieval augmented generation for large language models in healthcare: A systematic review,” PLOS Digit. Health, vol. 4, no. 6, p. e0000877, Jun. 2025.
Y. He, X. Zhu, D. Li, and H. Wang, “Enhancing Large Language Models for Specialized Domains: A Two-Stage Framework with Parameter-Sensitive LoRA Fine-Tuning and Chain-of-Thought RAG,” Electronics, vol. 14, no. 10, 2025.
J. A. H. Álvaro and J. G. Barreda, “An advanced retrieval-augmented generation system for manufacturing quality control,” Adv. Eng. Inform., vol. 64, Mar. 2025.
Ö. Karaduman and G. Gülhas, “Blockchain-enabled supply chain management: A review of security, traceability, and data integrity amid the evolving systemic demand,” Appl. Sci., vol. 15, no. 9, 2025.
W. A. H. Ahmed and B. L. MacCarthy, “Blockchain-enabled supply chain traceability – How wide? How deep?,” Int. J. Prod. Econ., vol. 263, Sep. 2023.
Y. Chun Tie, M. Birks, and K. Francis, “Grounded theory research: A design framework for novice researchers,” SAGE Open Med., vol. 7, p. 2050312118822927, Jan. 2019.
S. Jiang et al.,” ARGUS: Retrieval-Augmented QA System for Government Services,” Electronics, vol. 14, p. 2445, 2025.
S. J. van Rensburg, “End-user perceptions on information security,” J. Glob. Inf. Manag., vol. 29, no. 6, Jan. 2021.
T. Theys, P. Mechant, L. De Marez, and J. Saldien, “Understanding user perceptions of personal data stores: A prototype-driven multi-scenario study,” Int. J. Hum.-Comput. Interact., pp. 1–37, 2025.
B. Culiberg, M. K. Koklic, M. Kukar-Kinney, and I. Vida, “Vulnerability and perceived risks in the peer-to-peer sharing economy,” Int. J. Consum. Stud., vol. 48, no. 2, p. e13028, 2024.
Y. Dong et al., “Safeguarding large language models: A survey,” Artif. Intell. Rev., vol. 58, no. 12, p. 382, 2025.
