CEUR-WS.org/Vol-3957 - Workshops at the International Conference on Intelligent User Interfaces (IUI) 2025

CEUR-WS.org/Vol-3957 - Workshops at the International Conference on Intelligent User Interfaces (IUI) 2025
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
Carmen Santoro
Ziang Xiao
Department of Computer Science
University of Helsinki
HIIS Laboratory
ISTI-CNR
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
A User-in-the-loop Digital Twin for Energy Consumption Prediction in Smart Homes (short paper)
1-8
Davide Guizzardi
Barbara Rita Barricelli
Daniela Fogli
"Loss in Value": What it revealed about WHO an explanation serves well and WHEN (short paper)
9-15
Md Montaser Hamid
Jonathan Dodge
Andrew Anderson
Margaret Burnett
User Studies in Human-Feature-Integration
16-29
Yixin Li
Lucas Lefebvre
Sonali Parbhoo
Finale Doshi-Velez
Isaac Lage
Talking Back - human input and explanations to interactive AI systems
30-43
Alan Dix
Tommaso Turchi
Ben Wilson
Anna Monreale
Matt Roach
Explainable Biomedical Claim Verification with Large Language Models
44-57
Siting Liang
Daniel Sonntag
Context-dependent Explainable Daily Automations
58-68
Simone Gallo
Sara Maenza
Andrea Mattioli
Fabio Paternò
XFERa: Xplainable Emotion Recognition for improving transparency and trust (short paper)
69-77
Nicola Macchiarulo
Berardina De Carolis
Corrado Loglisci
Vito Nicola Losavio
Maria Grazia Miccoli
Giuseppe Palestra
Explainable Artificial Intelligence Across Various Scales of Interaction and Experience, From Wearable to Ambient (short paper)
78-83
Radu-Daniel Vatavu
Interactive Visual Exploration of Latent Spaces for Explainable AI: Bridging Concepts and Features
84-94
Carlo Metta
Eleonora Cappuccio
Salvatore Rinzivillo
Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness
95-111
Ulysse Maes
Lien Michiels
Annelien Smets
Human-Centered Design for Accessible and Sustainable XAI in Healthcare (short paper)
112-118
Giovanni Arras
Tommaso Turchi
Giuseppe Prencipe
Giuseppina Sgandurra
Toward a Human-Centered Metric for Evaluating Trust in Artificial Intelligence Systems (short paper)
119-127
Andrea Esposito
Giuseppe Desolda
Rosa Lanzilotti
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
Insights for Proactive Agents: Design Considerations, Challenges, and Recommendations
128-139
Anargh Viswanath
Hendrik Buschmeier
Toward Proactive Dialogic AI Agents
140-151
Sofia Brenna
Elisabetta Jezek
Bernardo Magnini
Designing Proactive Voice Interfaces: Key Factors for Office Settings (short paper)
152-160
Shashank Ahire
Michael Rohs
Implicit Interactions in Proactive Systems: Evaluation Challenges and Adaptations for Nielsen's Heuristics (short paper)
161-169
Alba Bisante
Alan Dix
Emanuele Panizzi
Stefano Zeppieri
Designing and Evaluating Human-Centred AI Systems: Best-Practices from a Multidisciplinary View (short paper)
170-178
Giuseppe Desolda
Andrea Esposito
Rosa Lanzilotti
Antonio Piccinno
A Vision for Room-scale AI Interaction
179-189
Carl Oechsner
Jan Leusmann
Xuedong Zhang
Thomas Weber
Sven Mayer
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
Towards Improving Visual Chatbot Builders with Intent-based Copilots (short paper)
190-199
Emanuel Lacic
Petra Fribert
Anamarija Lukac
Ivica Lovric
Exploring Industry Practices and Perspectives on AI
Attribution in Co-Creative Use Cases
200-210
Jessica He
Hyo Jin Do
ACE: Moving toward Co-Investigation with the Agentic Code Explorer
211-224
Dario Andres Silva Moran
Kristina Brimijoin
Gabriel Enrique Gonzalez
Stephanie Houde
Michael Muller
Michelle Brachman
Justin D. Weisz
Online Storytelling Spaces: Exploring Participants' Perceptions of Overt and Covert AI Agents
225-235
Roi Alfassi
Angelora Cooper
Zoe Mitchel
Mary Calabro
Orit Shaer
Osnat Mokryn
Fostering Co-creativity with Tangible Materials
236-252
Johanna Okerlund
Bethany Vasquez
Zoe Mitchell
Orit Shaer
Designing an Agentic AI Assistant for Chemical Discovery
253-265
Siya Kunde
Stephanie Houde
Rachel K. E. Bellamy
MetricMate: An Interactive Tool for Generating Evaluation
Criteria for LLM-as-a-Judge Workflow
266-278
Simret Araya Gebreegziabher
Charles Chiang
Zichu Wang
Zahra Ashktorab
Michelle Brachman
Werner Geyer
Toby Jia-Jun Li
Diego Gómez-Zará
Conceptualizing Agency: A Framework for Human-AI Interaction
279-289
Alexander Zhang
Lav R. Varshney
The Accessibility Landscape of Co-Creative AI Systems: Analysis, Insights and Recommendations
290-301
Makenzie Preston
Jeba Rezwana
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
ExpliCareNEXT: Human-Centered Explainable AI Solutions for Nursing Care (short paper)
302-310
Julia Hermann
Sebastian van Ledden
Christian Meske
Enrico Löhrke
Edwin Naroska
Todor Dimitrov
Sabahat Ölcer
Aysegül Dogangün
TherapyView: Visualizing Therapy Sessions with Temporal Topic Modeling and AI-Generated Arts (short paper)
311-318
Baihan Lin
Stefan Zecevic
Djallel Bouneffouf
Guillermo Cecchi
Exploring a Screensaver-Based System for Visualizing Health Status to Reduce Presenteeism: A Preliminary Evaluation
319-332
Sana Ozono
Year Nakamura
Yutaka Arakawa
The Development of an AI-Assistant to Therapists in a Chat-based Psychological Intervention: Gathering Users' First Impressions of the Experience
333-350
Neha Deshpande
Mariam Fishere
Stefan Hillmann
Jorge P. Marqués
Catarina B. Ferreira
Sofia Silva
Ricardo Barroso
Klaus M. Beier
A User-Centric Adaption Model for Document Visualizations with Different Levels of Detail within a Consumer Health Information System (short paper)
351-359
Mariia Tytarenko
Christian Wolfgang Burtscher
Daniel Atzberger
Adrian Jobst
Willy Scheibel
Stefan Lengauer
Tobias Schreck
An AI-driven Clinical Decision Support System for the Treatment of Diabetic Retinopathy and Age-related Macular Degeneration
360-370
Robert Andreas Leist
Hans-Jürgen Profitlich
Daniel Sonntag
Can Generative AI Support Patients' & Caregivers' Informational Needs? Towards Task-Centric Evaluation Of AI Systems
371-390
Shreya Rajagopal
Jae Ho Sohn
Hari Subramonyam
Shiwali Mohan
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
A Pilot Study: Naive smart interfaces can cause accidents
391-401
Christian Arnold
Paul Robertson
Zoe Robertson
Robert Laddaga
Boris Katz
Andrei Barbu
CalPal: An Intelligent Multimodal Digital Wall Calendar (short paper)
402-408
Devin Murphy
Jenny Moralejo
Paul Pu Liang
Generative AI's aggregated knowledge versus web-based curated knowledge (short paper)
409-418
Ted Selker
Yunzi Wu
SecureLLM: New private and confidential interfaces with LLMs
419-429
Abdulrahman Alabdulkareem
Christian Arnold
Yerim Lee
Pieter M Feenstra
Boris Katz
Andrei Barbu
TextVision: A more efficient way to work with research
430-443
Melis Aslan
Maximilian Bosse
Daniel Ehlers
Marlon Hinz
Philipp Olschewski
Jannik Podszun
Elias Scharlach
Leon Selzer
Yukun Wu
Aliki Anagnostopoulou
Daniel Sonntag
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
Social Robot Assistant for Group Interactions with Secondary School Students: A Participatory Design Study (short paper)
444-452
Manith Adikari
Annie O'brien
Suzanne Hamilton
Alexandra Hennessey
Samuele Vinanzi
Angelo Cangelosi
Graph of Goal-Oriented Thoughts: Design and Implementation of LLM Agents (short paper)
453-464
Dario Badagliacca
Gabriele Caruso
Agnese Augello
Luca Sabatucci
Pepper-based serious games for older adults: initial experiences in real-world settings (short paper)
465-473
Giulio Canapa
Benedetta Catricalà
Marco Manca
Fabio Paternò
Carmen Santoro
Eleonora Zedda
Enhancing a Conversational Agent with Social Cues: An Investigation into the Impact of Shared Identity and Goal Setting
474-489
Nikki Mae Evers
Iris Hendrickx
Multimodal Physiological Sensing for Adaptive Learning Environments (short paper)
490-496
Alessio Ferrato
Lorenzo Battisti
Giorgio Biancini
Marco Napoleone
Sabrina Fagioli
Carla Limongelli
Mauro Mezzini
Davide Nardo
Giuseppe Sansonetti
A Comparative Analysis of Social Media Content on Migration in Italy and the United States (short paper)
497-505
Gian Marco Francavilla
Giuseppe Sansonetti
Fabio Gasparetti
Alessandro Micarelli
Attention-Capture Damaging Patterns in UI Design: In Search of a Socio-Technical Mitigation Strategy (short paper)
506-515
Tales Gomes
Daniel Schneider
António Correia
Inclusive Interactions for Place-Belongingness: Lessons fron Citizen Science
516-530
Hesam Mohseni
Johanna Silvennoinen
António Correia
How Do Bias Strategies and Appearance Shape Avatar Preferences?: Toward the Development of Avatars for Health Support
531-543
Sana Ozono
Carolin Schindler
Yugo Nakamura
Yutaka Arakawa
Wolfgang Minker
Towards an Ontology of Human Explanations of Robotic Behavior
544-555
Maria Rausa
Agnese Augello
Antonio Lieto
On the usability of generative AI: Human generative AI (short paper)
556-565
Anna Ravera
Cristina Gena
Towards Personal Robotics: An Analysis of the State of the Art (short paper)
566-574
Aurora Toma
Davide Lofrese
Giuseppe Palestra
Berardina De Carolis
Use of de-polarizing techniques to influence students in a Cultural Heritage setting (short paper)
575-579
Alan Wecker
Tsafrir Goldberg
Tal Tabashi
Joel Lanir
Tsvi Kuflik
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
Can Less Be More? Understanding the Relation of Expertise and Automation Patterns in Medical XAI (short paper)
580-588
Anton de Vries
Thomas Franke
Tim Schrills
Designing AI Systems for Mental Model Development (short paper)
589-594
Michael Hoefer
Keep talking and nobody decides: How can AI augment users' ability to detect misinformation while balancing engagement and workload? (short paper)
595-602
Maged Mortaga
Marvin Sieger
Lilian Kojan
Hendrik Nunner
Leonard Stellbrink
André Calero Valdez
Tim Schrills
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