Vol-3957
urn:nbn:de:0074-3957-X

Copyright © 2025 for the individual papers by the papers' authors. Copyright © 2025 for the volume as a collection by its editors. This volume and its papers are published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).



IUI-WS 2025
Workshops at the International Conference on Intelligent User Interfaces (IUI) 2025


Joint Proceedings of the ACM IUI 2025 Workshops
co-located with the 30th Annual ACM Conference on Intelligent User Interfaces (IUI 2025)

Cagliari, Italy, March 24th, 2025.


Edited by

Dorota Glowacka 1
Carmen Santoro 2
Ziang Xiao 3

1 Department of Computer Science, University of Helsinki
2 HIIS Laboratory, ISTI-CNR
3 Department of Computer Science, Johns Hopkins University




Table of Contents

Summary: This volume includes the proceedings of 7 workshops, which accepted a total of 55 papers.

Workshop 1: Adaptive XAI: Advancing Intelligent Interfaces for Tailored AI Explanations (2nd Edition) (AXAI)


Organizers: Tommaso Turchi (University of Pisa, Italy), Alessio Malizia (University of Pisa, Italy), Fabio Paternò (CNR - ISTI, Italy), Simone Borsci (University of Twente, Netherlands), Alan Chamberlain (University of Nottingham, United Kingdom), Andrew Fish (University of Liverpool, United Kingdom)

As artificial intelligence becomes increasingly embedded in daily decision-making processes, the need for effective communication between humans and AI systems grows more crucial. The Adaptive XAI (AXAI) workshop, now in its second edition, focuses on developing intelligent interfaces that can adaptively explain AI's decision-making processes. Building on the success of our inaugural event at IUI 2024, this workshop continues to explore the intersection of Explainable AI and adaptive user interfaces, emphasizing the development of interfaces that dynamically adapt to create explanations that resonate with diverse users. In line with the human-centric principles of the Future Artificial Intelligence Research (FAIR) project, we examine how emerging technologies such as conversational agents and Large Language Models can enhance AI explainability while ensuring explanations remain malleable and responsive to users' evolving cognitive states and contextual needs.

More details here.

Workshop 2: Workshop on Best Practices and Guidelines for Human-Centric Design and Evaluation of Proactive AI Agents (BEHAVE AI)


Organizers: Matthias Kraus (University of Augsburg, Germany), Sebastian Zepf (Mercedes-Benz AG), Rebecca Westhäußer (Mercedes-Benz AG), Isabel Feustel (Ulm University, Germany), Nima Zargham (University of Bremen, Germany), Ilhan Aslan (Aalborg University, Denmark), Justin Edwards (University of Oulu, Finland), Sven Mayer (LMU Munich, Germany), Dimosthenis Kontogiorgos (Massachusetts Institute of Technology, USA), Nicolas Wagner (Otto-Friedrich-University Bamberg, Germany), Elisabeth André (University of Augsburg, Germany)

The last years have seen a significant rise in interest in highly autonomous and proactive agents fueled by the progress of AI. While there is various research on the design, implementation, and evaluation of proactive agents, there remains a critical gap in the methodologies used for both design and evaluation, which are largely informed by reactive system design principles. Our fullday multidisciplinary workshop brings together researchers and practitioners from the IUI community in academia and industry to understand the challenges of designing and evaluating proactive agents in a human-centric manner. We will reflect on existing evaluation methods, identify challenges in designing proactive systems, and discuss potential solutions, best practices, and human-centric guidelines to bridge these gaps. Ultimately, our goal is to map out key focus areas and research challenges, fostering strong interdisciplinary relationships within and across fields related to Artificial Intelligence (AI) and Human-Computer Interaction (HCI).

More details here.

Workshop 3: 6th Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN 2025)


Organizers: Osnat Mokryn (University of Haifa, Israel), Orit Shaer (Wellesley College, USA), Werner Geyer (IBM Research AI), Mary Lou Maher (UNC Charlotte, USA), Justin D. Weisz (IBM Research AI), Daniel Buschek (University of Bayreuth, Germany), Lydia B. Chilton (Columbia University, USA)

Generative Artificial Intelligence (GAI) models capable of complex tasks are revolutionizing areas previously considered to define humanity, such as creativity, design, and knowledge work. Research reports that Human-GAI co-creation processes can enhance creativity and even foster a sense of empowerment. A key innovation is the intent-based outcome specification, where users define desired results through natural language, sketches, or gestures, thus shifting control from users to AI models. This paradigm enables new forms of co-creation while presenting challenges in creating effective and safe outcome specifications. This workshop aims to investigate the design, implementation, and evaluation of intent-based co-creative experiences that boost human creativity in work, play, and education across text, images, audio, code, and video. Key questions focus on how creativity support can guide generative AI development and how to leverage generative models for positive user experiences. By uniting researchers and practitioners from Human-Computer Interaction (HCI) and AI, the workshop seeks to deepen understanding of human-AI cocreative interactions and explore opportunities and challenges in developing meaningful and safe generative systems.

More details here.

Workshop 4: Workshop on Intelligent and Interactive Health User Interfaces (HealthIUI)


Organizers: Peter Brusilovsky (University of Pittsburgh, USA), Denis Parra (Pontificia Universidad Católica, Chile), Behnam Rahdari (University of Pittsburgh, USA), Shriti Raj (Stanford University, USA), Helma Torkamaan (TU Delft, Netherlands)

The HealthIUI workshop explores the integration of intelligent user interfaces in health and care, focusing on AI-driven solutions that enhance user engagement, support clinical decision-making, and improve health information access. The workshop brings together experts from human-computer interaction, AI, and healthcare to address challenges such as transparency, usability, and ethical considerations in AI-assisted health applications. Topics covered include generative AI for patient and caregiver support, AI-powered clinical decision support, adaptive visualization for consumer health information, and explainable AI in nursing care. Through paper presentations and discussions, the workshop fosters interdisciplinary collaboration to advance intelligent health interfaces that balance technical innovation with user-centric design principles

More details here.

Workshop 5: Mixed-Initiative Next-gen Design: Workshop on Blending Agents and Direct Manipulation for Harnessing LLMs (MIND)


Organizers: Karthik Dinakar (Pienso Inc), Henry Lieberman (MIT CSAIL), Meng-Hsin Wu (Pienso Inc)

Since the 1980s, a key debate in human-centered computing involving machine learning at IUI is between agent-driven systems and direct manipulation. The explosion of Large Language Models (LLMs), particularly auto-regressive as agents serving as chatbots, generative search, and work automation tools, has also brought with it inherent limitations. We posit that efforts to address and alleviate these LLM challenges-hallucinations, unpredictable outputs, lack of transparency, and difficulties in customization-cannot be solved through algorithmic improvements alone but require elevated mixed-initiative interface design at the heart of the IUI community. This workshop aims to bridge the gap between agent-driven automation and direct manipulation by exploring mixed-initiative interaction models that blend the strengths of both paradigms to empower end-users seeking to harness LLMs.

More details here.

Workshop 6: Social and Cultural Integration with Personalized Interfaces (SOCIALIZE 2025)


Organizers: Berardina De Carolis (University of Bari, Italy), Fabio Gasparetti (Roma Tre University, Italy), Cristina Gena (University of Torino, Italy), Styliani Kleanthous (Open University of Cyprus, Cyprus), Giuseppe Sansonetti (Roma Tre University, Italy)

This is the ffth edition of the SOcial and Cultural IntegrAtion with PersonaLIZEd Interfaces (SOCIALIZE) workshop. This year's event, like those before it, focuses on bringing together technology enthusiasts to break down barriers - whether they are cultural, social, or linguistic. We especially want to help people who struggle with making connections. In this context, social robots could play a vital role in achieving these ambitious aims. This year's edition has been particularly successful in terms of submissions. After the review process, 13 articles were accepted, all addressing relevant and timely topics. The authors hope that their presentations will inspire fruitful and engaging discussions among the participants.

More details here.

Workshop 7: Strengthening Engineering Psychology for Human-Algorithm Interactions (STEP-HAI)


Organizers: Patricia Kahr (Eindhoven University of Technology, Netherlands), Tim Schrills (University of Lübeck, Germany), Thomas Franke (University of Lübeck, Germany)

As intelligent systems become increasingly integrated into our daily lives, understanding human cognition, motivation, and behavior is essential to designing effective and trustworthy algorithmic systems. Although empirical research on human-algorithm interaction (HAI) is growing rapidly, we nonetheless observe that theoretical frameworks often lack the integration of foundational principles from cognitive and engineering psychology. The STEP-HAI workshop (Strengthening Theoretical and Empirical Principles in Human-AI Interaction) addresses this challenge by bringing together researchers and practitioners to discuss psychological frameworks, experimental methodologies, and measurement approaches in HAI. Key topics include information processing, cognitive and behavioral factors, and the influence of user perceptions, such as trust or situational awareness, in algorithm-assisted decision-making. By fostering cross-disciplinary dialogue between researchers and practitioners, STEP-HAI aims to define research priorities and bridge the gap between theoretical models and real-world AI applications, promoting more robust, psychologically grounded approaches to AI development.

More details here.
2025-03-18: submitted by Ziang Xiao, metadata incl. bibliographic data published under Creative Commons CC0
2025-05-02: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|