UKG

Knowledge graphs (KGs) have emerged as a powerful paradigm for representing and managing complex information, underpinning numerous applications from search engines to personalized recommendations. However, the true potential of KGs can only be realized if users effectively utilize them. This workshop focuses on the critical intersection of users and KGs. It explores how individuals interact with KGs, their challenges, and the innovative solutions that can bridge the gap between KG technology and user needs. We aim to foster discussions that improve the usability, accessibility, assessment, and adoption of KGs in real-world scenarios. We invite submissions presenting user studies, case studies, novel applications of KGs designed with user-centricity and explainability in mind, and research exploring the cognitive and interactional aspects of KG use. This workshop aims to foster a vibrant discussion on the future of user-centred KG design and development. It will feature paper presentations, interactive discussions, demos, and a panel session to encourage engagement between researchers and practitioners.

Motivation

While the technical aspects of KG construction and reasoning have seen significant advancements, the human element often remains underexplored. Many KGs, despite their rich semantic structure, are not readily accessible or understandable to their intended users. This disconnect can hinder the adoption and effective use of KGs in various domains. This workshop is motivated by the growing recognition of the crucial role of user interaction in the success of KG-based systems. There is a need to understand:

• User perception and interaction with KGs: how different user groups understand, trust, and work with KG-based systems in practice.
• Challenges in querying, exploring, and contributing to KGs: where users struggle (e.g., mental models, terminology, feedback, errors) and what support they need.
• Designing intuitive and user-friendly KG applications: interaction patterns, guidance, and workflows that lower barriers and improve task success.
• Metrics and methodologies for evaluating user interaction with KGs: appropriate measures, study designs, and reproducible protocols for comparing KG interfaces and experiences. Assessing explainability, usability, and user value of KG-driven tools (beyond accuracy: effort, confidence, trust, and adoption).
• User-centred evaluation methods for KG systems: lab and field studies, longitudinal designs, mixed methods, accessibility and inclusion).
• Human-LLM-KG collaboration: how users work with LLM-powered KG interfaces and assistants, and how to evaluate reliability, controllability, transparency, and accountability.
• Visualization and interaction for user-facing KGs: approaches that support exploration, sensemaking, debugging, validation, and communication of KG-based results.

By bringing together researchers and practitioners from diverse backgrounds, this workshop aims to identify key research directions and foster collaborative efforts to address these challenges. A deeper understanding of user interaction with KGs is essential for unlocking the full potential of this technology and enabling its widespread adoption. This topic is especially timely as KGs increasingly drive real-world systems, such as retrieval-augmented generation (RAG), enterprise search, conversational agents, and recommender systems, yet systematic research on user interaction with KGs remains limited.

Audience

The workshop’s target audience includes academics and industrial players, especially those working on KG projects involving diverse stakeholders and end-users. We aim for a high diversity of experience among participants, whether they work in fundamental, applied, or industrial research. The workshop targets a diverse audience, including:

• Researchers and practitioners in the field of knowledge graphs (KGs) and semantic technologies.
• UX designers and human-computer interaction (HCI) specialists working with KGs.
• Industry professionals developing KG-based applications.
• Scholars studying the usability and cognitive aspects of semantic technologies.
• Researchers in knowledge representation and reasoning or human-computer interaction (HCI).
• Domain experts who utilize KGs in their respective fields.
• Students interested in learning about the intersection of KGs and user interaction .

Attendees will gain insights into user behaviour, evaluation methods, and real-world applications of KGs, fostering interdisciplinary collaboration.

Contributions

• Full (12-15 pages) or short (5-8 pages) research papers.
• In Use and Experience papers (12-15 pages), as well as demo papers (4-6 pages).
• Position and Vision papers (4-6 pages)

Format

• Submissions should follow the guidelines of IOS Press.
• Authors need to use the Word template or LaTeX template provided by IOS Press. Overleaf users can copy the project from here (follow instructions in the abstract).
• Abstract submission is mandatory for all papers. To aid the review and bidding process, we highly encourage authors to submit structured abstracts.
• All papers and abstracts have to be submitted electronically via EasyChair (see below).
• Submissions must be in English.
• Submissions must adhere to the fair use of Large Language Models, and they must explicitly and visibly include a Declaration on Generative AI, at the end of the paper. Please refer to the SEMANTiCS full policy for more details.
• Submissions are expected to address relevant ethical issues and to provide estimates of the environmental footprint of the presented work.
• Submissions must be anonymous; the reviewing process is double-anonymous, but reviewers will be able to disclose their identities if they wish, by signing their reviews.
• Accepted papers will be published in open access proceedings by IOS Press, and the text of all the reviews (excluding the scores) of all the accepted papers will be posted on the conference website and will be archived on Zenodo as publicly available material, under CC BY 4.0 license.
• At least one author of each accepted paper must present it in person and therefore register for the conference at the ONSITE rate.

Review and Publication

• Please, share your contribution before the deadline through the OpenReview platform. The accepted contributions will be published in the proceedings of the workshop through CEUR-WS. Each accepted paper needs to be presented by one of the authors at the workshop.

• Attention, those submitting to the workshop must be aware of OpenReview's moderation policy for newly created profiles:
  • New profiles created without an institutional email will go through a moderation process that can take up to two weeks.
  • New profiles created with an institutional email will be activated automatically.
  • Camera Ready Instructions is available here.

Submit Now

TBD

For information about the conference venue, please refer to the SEMANTiCS website.