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

Abstract

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.