Theoretical Framework for Completeness and Consistency of Knowledge in Generative AI Large Language Models

An Analytical Framework for the Evolution of Large Language Models: From Reasoning to LLM-as-a-Judge

This study aims to develop an integrative computational-analytical framework for explaining the functional evolution of large language models through four interrelated dimensions: Reasoning, Retrieval and Knowledge Grounding, Alignment, and Judging, collectively represented by the RRAJ framework. The study adopts a systematic analytical literature review of research published between 2020 and 2026, drawing on Scopus, Web of Science, and IEEE Xplore, and applying comparative and thematic analysis to trace major technical transformations and functional relationships across the four dimensions. The findings indicate that the evolution of large language models is no longer driven primarily by model scaling, but increasingly by system scaling, in which knowledge, computation, and control are distributed across model parameters, contextual information, external knowledge sources, inference-time computation, and evaluation mechanisms. The analysis further reveals a shift from isolated capabilities toward functional convergence among RRAJ components, with LLM-as-a-Judge emerging as an important transition that enables evaluation to support diagnosis, feedback, and correction. The study concludes that future LLM systems are likely to become more adaptive, verifiable, self-evaluating, and self-correcting. It further recommends improving judge reliability, error traceability, and human oversight in high-risk applications, while exploring judge-governed execution as a future extension for agentic and robotic systems.

Towards principled knowledge editing methods for large language model reasoning

What Aspects of Tacit Knowledge Are Structurally Excluded from Generative AI? : A Conceptual Framework of Mediation, Structure, and Representation

Recent advances in generative AI, particularly large language models and multimodal foundation models, have renewed interest in whether tacit knowledge can be learned or reproduced by machines. While prior studies emphasize the growing ability of generative AI to approximate patterns of human reasoning, judgment, and action, comparatively little attention has been paid to what aspects of tacit knowledge are excluded by design. This paper addresses this gap by asking a conceptual question: which aspects of tacit knowledge are structurally excluded from contemporary generative AI research? Rather than treating tacit knowledge as a single implicit capability, this study reorganizes prior research into three analytical perspectives: mediation, structure, and representation. From this viewpoint, tacit knowledge is sustained by processes that translate practice into communicable forms, by social and cultural structures that stabilize judgment and action, and by representational practices that constitute tacit knowledge as an object of analysis. These perspectives are then used to examine recent developments in generative AI. The analysis shows that current generative AI systems primarily engage with the externalized outcomes of tacit knowledge, such as observable reasoning patterns or action trajectories, while leaving its formative conditions unaddressed. Processes of mediation, social and institutional structures, and reflexive representational practices remain outside model design. These limitations are not merely technical but reflect structural design choices embedded in contemporary AI research. By clarifying these boundaries, this paper provides a conceptual framework for reconsidering the division of roles between human practice and generative AI in future socio-technical systems.

Interpretability in the Era of Large Language Models: Mechanistic Methodology, Empirical Practices, and Applications

This tutorial provides a comprehensive, end-to-end view of LLM interpretability, transitioning from microscopic neural analysis to macroscopic application and deployment, and explores how these interpretability paradigms scale and inspire the design of frontier architectures, agentic systems, and thinking models.

From Tacit Knowledge to Structured Documents: A Framework for Knowledge Elicitation

Recent advances in Large Language Model (LLM) “agent” systems have moved language models beyond single-turn generation toward goal-directed workflows that can plan, ask clarifying questions, and iteratively refine outputs. In parallel, retrieval-augmented generation (RAG) has become a practical way to ground these agents in enterprise knowledge—enabling models to leverage internal documentation and policies without expensive and recurring retraining. However, RAG is only as strong as the underlying corpus: when key information is missing, outdated, or fragmented, retrieval cannot fill the gaps. In many organizations, assembling high-quality, up-to-date documents remains a persistent bottleneck, limiting both the reliability of downstream applications and the speed at which knowledge can be operationalized. To address this, we introduce the Assistant-Scribe-Knowledge Checker (ASK) framework for generating structured specification documents through guided interviews. ASK decomposes the end-to-end workflow into three specialized LLM agents: an Assistant that asks questions to the user and steers the interview through adaptive follow-ups; a Scribe that continuously summarizes what has been said and records it into a schema-constrained specification document with explicit content requirements; and a Knowledge Checker that evaluates the evolving document against those specifications, detects gaps or weakly supported entries, and advises the Assistant on the next best questions to ask to reach the desired completeness and quality. This separation supports seamless document creation while improving quality control over content, structure, and coverage. By distributing responsibilities across three lightweight, role-specific agents, ASK reduces reliance on a single large model and enables modular scaling across teams and domains. We evaluated the ASK framework in a consulting-firm setting where consultants are required to produce project “return-of-experience” documents (successes, failures, challenges, and solutions) to capture reusable knowledge. Compared to documents authored manually, ASK-guided interviews consistently produced more complete, better-structured, and higher-quality specifications with less variability across authors. Beyond measurable quality gains, consultants also reported a clear preference for the interview-based workflow, citing lower effort and a more natural way to articulate tacit project knowledge.

Exploring the Interplay of Theory of Mind, Logic Validation, and Advanced Retrieval in LLM-Based Multi-Agent Systems

This study contributes to the field of artificial intelligence by offering a structured approach to building, testing, and refining multi-agent architectures that balance knowledge grounding, perspective modelling, and reasoning validation.