About the Workshop

The emergence of Large Language Models (LLMs) has revolutionized Conversational User Interfaces (CUIs), enabling more dynamic, context-aware, and human-like interactions across diverse domains, from social sciences to healthcare. However, the rapid adoption of LLM-based personas raises critical ethical and practical concerns, including bias, manipulation, and unforeseen social consequences. Unlike traditional CUIs, where personas are carefully designed with clear intent, LLM-based personas generate responses dynamically from vast datasets, making their behavior less predictable and harder to govern. This workshop aims to bridge the gap between CUI and broader AI communities by fostering a cross-disciplinary dialogue on the responsible design and evaluation of LLM-based personas. Bringing together researchers, designers, and practitioners, we will explore best practices, develop ethical guidelines, and promote frameworks that ensure transparency, inclusivity, and user-centered interactions. By addressing these challenges collaboratively, we seek to shape the future of LLM-driven CUIs in ways that align with societal values and expectations.

Key Dates

Submissions Due:
June 15th, 2025 AOE

Notifications Sent:
On a rolling basis

Workshop Date:
July 8th, 2025

Submissions

Papers or expressions of interest should be sent to: cui.research.hub@gmail.com

Organizers

Smit Desai

Smit is an Assistant Professor at Northeastern University's College of Art, Media and Design. He studies user mental models of conversational agents using innovative methods like metaphor analysis. He applies this insight and his expertise in conversation design to develop voice-based AIs for social roles such as instructors and coaches. Additionally, he has served the HCI community in various roles, such as co-chair of Provocation Papers at CUI 2024 and co-organizer for workshops at CHI 2024, MUM 2024, and CUI 2024.

Mateusz Dubiel

Mateusz is a Research Associate in the Department of Computer Science at the University of Luxembourg, where he works on the development and evaluation of conversational agents. Specifically, his current research focuses on assessment of cognitive and usability implications of interfaces that feature speech and exploration of their potential to inspire positive behavioural change in users. He served as Short Papers Chair for CUI 2022 and was one of General Chairs for CUI 2024.

Nima Zargham

Nima is a postdoctoral researcher in the Digital Media Lab at the University of Bremen. His research focuses on human-centered approaches for designing speech-based systems that elicit desirable user experiences. Nima has previously organized CUI-related workshops at notable conferences such as ACM/IEEE HRI 2023, ACM CUI 2023, ACM CUI 2024, and ACM CHI 24. Additionally, he served as a local chair at the ACM CHI-PLAY 2022 conference. His research efforts have resulted in publications featured in prestigious HCI venues, including ACM's CHI, CUI, and CHI-PLAY.

Thomas Mildner

Thomas is a postdoctoral researcher at the Digital Media Lab at the University of Bremen. His research focuses on ethical and responsible design and online well-being, with studies exploring so-called dark patterns in social media as well as conversational technologies. To this end, Thomas collaborated to develop the CUI expectation cycle to align system capabilities with user expectations and an ontology for dark patterns. His research has been published in venues including CHI, DIS, and CUI.

Laura Spillner

Laura is a PhD student at the Digital Media Lab at the University of Bremen. Her research focuses on the development of explainable AI and hybrid AI in the field of language understanding and the interaction between humans and AI in natural language.

Keynote

Dr. Marta Ziosi

To inspire discussions, we are delighted that Dr. Marta Ziosi has agreed to give a keynote at this event. Marta is an AI policy expert who worked for institutions such as DG CNECT at the European Commission, the Berkman Klein Centre for Internet & Society at Harvard University, The Montreal International Center of Expertise in Artificial Intelligence (CEIMIA) and The Future Society. Previously, Marta was a Ph.D. student and researcher on Algorithmic Bias and AI Policy at the Oxford Internet Institute. She is also the founder of AI for People, a non-profit organisation whose mission is to put technology at the service of people. Currently, Marta serves as vice-chair to co-develop the General-Purpose AI Code of Practice of the European Commission, specifically risk identification and assessment, including evaluations.

Call For Papers

Prospective participants will be invited to submit either a position paper (2-3 pages) or a statement of interest. Priority will be given to those submitting position papers, as they will help ground the workshop discussions in concrete ideas and research. To ensure a productive setting, participation will be limited to 20 individuals. The selection process will prioritize diversity, aiming to assemble a group that reflects a wide range of backgrounds, expertise, and perspectives relevant to the workshop’s themes. By carefully curating the participant list, we aim to create an environment conducive to meaningful dialogue, collaboration, and knowledge exchange.