Aug 2026· International Journal of Engineering Science and Information Technology· 0 citations
TL;DR
A literature-based architectural framework for reliable knowledge retrieval systems that separates external knowledge management from LLM-based reasoning and generation is developed and indicates that reliable LLM deployment should be treated as an end-to-end architectural problem rather than solely a model-performance problem.
Abstract
The increasing deployment of large language models (LLMs) in enterprise environments creates reliability challenges related to hallucination, factual inconsistency, limited knowledge traceability, uncertainty, and operational efficiency. This study develops a literature-based architectural framework for reliable knowledge retrieval systems that separates external knowledge management from LLM-based reasoning and generation. The framework synthesizes architectural mechanisms for knowledge representation, hybrid retrieval, reranking, evidence selection, context construction, response verification, provenance tracking, uncertainty handling, guardrails, and computational efficiency. The resulting architecture organizes these mechanisms into coordinated layers that control the flow of external evidence from knowledge sources to generated responses while supporting traceability and controlled abstention when sufficient evidence is unavailable. The architectural synthesis further identifies complementary strategies for enterprise deployment, including semantic caching, model routing, and human oversight, to balance reliability, scalability, and operational cost. The analysis indicates that reliable LLM deployment should be treated as an end-to-end architectural problem rather than solely a model-performance problem, with knowledge access, evidence quality, verification, provenance, and governance functioning as integrated system components. The proposed framework provides a structured foundation for designing maintainable, auditable, and reliable knowledge retrieval systems for enterprise and other high-stakes applications
This study proposes an LLM-powered knowledge management framework that combines Retrieval-Augmented Generation (RAG), semantic embeddings, enterprise-specific language models, and vector databases to transform enterprise data into actionable knowledge.
Farhan Malik, Zara Ahmed· International Journal of App...· 0 citations
In creating reliable and context-proper retrieval mechanism from dynamically changing organization repositories, Enterprise Retrieval-Augmented Generation (RAG) systems rely increasingly on mechanisms for ongoing ingestion of knowledge. This is often the case with the existing ingestion pipelines, which are semantically inconsistent, repeatedly regenerating vectors, leniently looking up vectors, and complexifying synchronizations when your repository is updated incrementally. The restrictions lower the likelihood of retrievals being accurate and impact the contextual accuracy of enterprise generative AI systems. This paper presents a new trustworthy and incremental enterprise knowledge ingestion framework called Evidence-Coupled Knowledge Resonance Architecture (EKRA) to tackle these issues. The proposed EKRA framework provides a semantic stabilization environment that can guarantee the continuation of context in the repository during the changes of the same. The framework incorporates semantic validation procedures, evidence retention, prioritized dependency reassessment and synchronization that allows for the retrieval consistency without the need to recreate full vector repositories. Moreover, the proposed architecture clearly has the property of fewest semantic disruptions, by maintaining a structure of relationships between knowledge that reflect their meanings, while preserving the evidence links, they carry, on incremental additions to the knowledge. Another framework enhancement is adaptive synchronization of impacted semantic areas within enterprise retrieval structures, which enhances the continuity of retrieval. Through experiments, it has been shown that the proposed EKRA framework is significantly more successful in achieving retrieval reliability, less synchronization difference, better semantic preservation, and can also better ensure incremental ingestion stability than current enterprise RAG ingestion methods. The proposed architecture will offer a flexible and scalable solution for dynamic enterprise knowledge space. The suggested EKRA framework obtained a total enterprise retrieval accuracy of 96.8% in incremental RAG knowledge ingestion procedures.
Chaitanya Devella· 2026 International Conferenc...· 0 citations
The Assistant-Scribe-Knowledge Checker (ASK) framework for generating structured specification documents through guided interviews is evaluated in a consulting-firm setting where consultants are required to produce project “return-of-experience” documents to capture reusable knowledge.
Sylvain Roudiere, Bianca Lento· European Conference on Knowl...· 0 citations
The emergence of Large Language Models (LLMs) has redefined how users interact with information in digital environments. However, their widespread and often indiscriminate integration has raised significant concerns regarding reliability and trustworthiness issues that are particularly critical when accessing digital libraries and historical archives. How can one leverage the generalization capacity of an LLM without losing the level of accountability required for an archival institution? In this paper, we present an agentic retrieval system designed to deliver more accurate and verifiable access to historical data while preserving much of the flexibility associated with unconstrained LLMs. As a contribution to historical document analysis, we compare traditional Retrieval-Augmented Generation (RAG) with an agentic GraphRAG architecture in their ability to deliver historical information under realistic conditions, including the presence of OCR and transcription errors. We introduce a semi-symbolic framework that integrates word-spotting techniques for post-OCR correction with a knowledge graph representation that enables the agent to access information through synthesized queries. The interleaved collaboration between word spotting and code generation allows the agent to construct strong retrieval queries that are robust to misinterpretation and hallucination, while still leveraging approximate search when noise and uncertainty, common in historical document analysis, would otherwise hinder precise retrieval.
S. Nicolau, Adrià Molina, O. R. Terrades et al.· IEEE International Conferenc...· 0 citations
For decades, search and recommendation systems have been optimized as distinct components within large-scale discovery platforms. The rise of generative AI is beginning to blur this boundary. At Spotify, we are exploring how large language models can evolve from tools that retrieve content into systems that reason over users, catalogs, and intent, while remaining steerable through natural language and user interaction. This talk presents lessons from deploying and studying generative retrieval and recommendation systems across Spotify's content ecosystem. I will describe how semantic identifiers enable language models to operate directly over large, heterogeneous catalogs, allowing search, recommendation, retrieval, explanation, and user understanding to be expressed within a common generative framework. I will discuss recent work on production-scale podcast discovery, language-steerable recommendation, and the NEO framework for unifying search, recommendation, and reasoning across multiple content types. These systems demonstrate how grounding language models in catalog entities and user behavior can improve discovery while preserving the flexibility of natural-language interaction. More broadly, they suggest a path toward discovery systems in which retrieval, recommendation, and reasoning are no longer separate stages, but capabilities of a shared generative model. Beyond model frameworks, I will discuss the emerging challenges of alignment and evaluation in discovery systems. Unlike traditional retrieval problems, generative recommendation often has many valid answers. I will present approaches for learning from large-scale behavioral signals, preference-aware optimization, and profile-aware LLM-as-a-judge evaluation, along with lessons from online experimentation at Spotify. These experiences suggest that future discovery systems will require new forms of personalization, controllability, and evaluation that extend beyond conventional ranking metrics. I will conclude with a research agenda for generative discovery systems, including language-steerable interfaces, unified retrieval-and-reasoning models, preference-aligned generation, and evaluation frameworks designed to measure user-specific relevance at scale. As search, recommendation, and conversational AI continue to converge, these directions point toward a new generation of discovery systems that can understand intent, reason over large catalogs, and help users navigate increasingly complex information spaces.
Paul N. Bennett· Proceedings of the 32nd ACM...· 0 citations
Generative AI is changing the role of knowledge in organisations. Traditional knowledge management (KM) systems have primarily supported storage, access and retrieval, assuming that knowledge is interpreted and applied by human users. In AI-enabled environments, however, organisational knowledge increasingly becomes a direct input into execution, shaping generated proposals, analyses, summaries, recommendations and other workflow outputs. This shift exposes a limitation of retrieval-oriented KM: fragmented, outdated or weakly governed knowledge can be amplified through AI-generated outputs, reducing consistency, reliability and trust. This paper introduces executable knowledge systems as a conceptual model for structuring organisational knowledge to support reliable human and AI-assisted execution. The term executable is used in a socio-technical sense. Knowledge does not necessarily become code, but is curated, validated and embedded into workflows so that it can guide outputs, decisions and actions. The paper distinguishes this concept from prior work on executable knowledge graphs and executable knowledge bases, which primarily focus on deterministic execution through rules, scripts or formalised representations. The paper further develops a framework of decay and compounding loops to explain how AI-enabled knowledge systems evolve over time. In decay loops, AI-generated outputs re-enter the knowledge environment without sufficient validation, allowing inconsistency and low-quality knowledge to accumulate. In compounding loops, curated knowledge assets are refined through governed feedback, domain ownership and controlled reuse, enabling improvements in reliability over time. The framework is informed by an exploratory case study within a global professional services organisation, where a curated knowledge environment was introduced to support AI-assisted workflows in the Retail, Consumer Products, Travel and Transportation domain. The evaluation compared outputs generated from a controlled, subject matter expert (SME)-validated knowledge dataset with outputs generated from an unconstrained organisational knowledge base. Findings indicate improved retrieval relevance and output quality when AI systems operate on validated knowledge assets. The paper contributes to KM research by reframing KM as a system design challenge for AI-enabled execution and by positioning governance, validation and feedback control as central mechanisms for reliable organisational knowledge use.
Sara Michelazzo, Parmeet Kaur, Saurabh Saxena· European Conference on Knowl...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
