Project Reports

Academic information environments are often characterized by heterogeneous, distributed, and insufficiently maintained data sources, which makes relevant information difficult to find and reuse. In this work, we present a knowledge-graph-based information system freeda, designed to provide accurate, traceable, and reliable information retrieval in the university context. We combine the knowledge graph with a retrieval-augmented generation (RAG) framework and large language models (LLMs), enabling natural-language exploration of structured data. As a proof of concept, we developed a full-stack web application.

This report presents an ongoing research project commissioned by the National Assembly Library of Korea to transition its thesaurus-based controlled vocabulary system toward an ontology-based concept management system. We cover the project’s goals, methodology, and current progress.

The Blue Core project completed development on a prototype in 2025, realizing the vision for a community-operated and owned BIBFRAME data store and providing a valuable environment for testing integrations with two open-source linked data editors: Sinopia and Marva. Thoroughly tested for scalability, metadata operations, and integration with local Library Services Platforms, the prototype informs plans for a Blue Core MVP that leverages agentic AI to enhance cataloger workflows.

This study examines how leading AI companies, including Anthropic, Google, Meta, and OpenAI, construct ethical commitments in their governance documents, and how these constructions are systematically shaped by metadata conditions such as document type, organizational structure, and temporal context. While prior work has increasingly examined AI ethics documents as governance instruments shaped by institutional interests, sectoral differences, and political motivations, these studies still primarily approach AI ethics documents at the level of themes, principles, stakeholder representation, and policy discourse. This research extends that literature by arguing that AI ethics documents function as metadata-conditioned moral grammars: dynamic linguistic architectures that distribute responsibility, prioritize values, structure anticipatory governance, and guide decision-making under conditions of uncertainty. It investigates how AI governance documents by major technology corporations function as discursive infrastructures for the construction of ethical meaning. It analyzes how ethical frames including safety, innovation, autonomy, responsibility, and societal benefit are prioritized, sequenced, contextualized, and relationally embedded within these documents. Rather than understanding such principles as static normative commitments, the study examines how their linguistic organization operates as a metadata-conditioned moral grammar that distributes responsibility, structures anticipatory governance, and legitimizes institutional authority in AI governance. It examines how responsibility is both explicitly and implicitly attributed across various agents, including the organization, the AI system, users, developers, and abstract institutional entities, through patterns of grammatical agency and semantic positioning, while also identifying the linguistic mechanisms, such as passive constructions, abstract nominalizations, hedging expressions, and conditional qualifiers that contribute to the diffusion or attenuation of responsibility.