Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Management
2026-07-27 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied whether combining large language models (LLMs) with Retrieval-Augmented Generation (RAG) can make them more reliable for tasks needing accurate information. They tested this by using local LLMs without powerful GPUs, linked to external knowledge sources, to help interpret legal documents continuously. Their results showed that adding RAG improved the accuracy and relevance of the model’s outputs, reduced mistakes, and allowed for easier updating of information without retraining the model. The authors suggest that these enhanced LLMs can act as parts of intelligent systems that support decision-making in complex legal environments.
Large Language Models (LLMs)Retrieval-Augmented Generation (RAG)Cognitive ComputingSemantic InterpretationRegulatory ManagementOn-premises DeploymentFactual ConsistencyTraceabilityKnowledge ManagementModel Retraining
Authors
Dariusz Nowak-Nova
Abstract
The aim of this article is to verify whether integrating large language models (LLMs) with the Retrieval-Augmented Generation (RAG) architecture enables their transformation from standalone generative models into components of cognitive computing infrastructure with enhanced epistemic reliability. The study proposes an architectural approach based on locally deployed LLMs operating in on-premises environments without high-end GPU accelerators and examines their applicability in supporting regulatory management processes requiring continuous analysis and interpretation of legal acts. The proposed solution combines local LLMs with external knowledge repositories, creating a hybrid cognitive architecture in which the language model performs semantic interpretation while the RAG layer provides controlled knowledge retrieval, contextualization, and traceability of information sources. The implementation was validated using the Ollama and LM Studio execution environments together with the Polish language models Bielik and PLLuM running on consumer-class hardware. The results demonstrate that augmenting LLMs with RAG significantly improves the factual consistency, domain specificity and normative precision of generated texts while reducing the risk of unsupported content generation. Furthermore, the study shows that integrating RAG introduces auditability, controlled knowledge management and dynamic updating of regulatory information without retraining the language model. The findings indicate that locally deployed LLMs enhanced with RAG should be regarded not merely as text generation tools but as semantic processing modules within cognitive computing infrastructures supporting regulatory compliance and organizational decision-making in environments characterized by high legal and informational volatility.