Listening to the Voices: Describing Ethical Caveats of Conversational User Interfaces According to Experts and Frequent Users
Thomas Mildner, Orla Cooney, Anna-Maria Meck, Marion Bartl, Gian-Luca Savino, Philip R. Doyle, Diego Garaialde, Leigh Clark, John Sloan, Nina Wenig, Rainer Malaka, Jasmin Niess
Abstract
Advances in natural language processing and understanding have led to a rapid growth in the popularity of conversational user interfaces (CUIs). While CUIs introduce novel benefits, they also yield risks that may exploit people’s trust. Although research looking at unethical design deployed through graphical user interfaces (GUIs) established a thorough understanding of so-called dark patterns, there is a need to continue this discourse within the CUI community to understand potentially problematic interactions. Addressing this gap, we interviewed 27 participants from three cohorts: researchers, practitioners, and frequent users of CUIs. Applying thematic analysis, we construct five themes reflecting each cohort’s insights about ethical design challenges and introduce the CUI Expectation Cycle, bridging system capabilities and user expectations while considering each theme’s ethical caveats. This research aims to inform future development of CUIs to consider ethical constraints while adopting a human-centred approach.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 312b0ba6-1546-4acc-9291-760fcfab6047Cited by top-tier papers6
- A Comparative Study of How People With and Without ADHD Recognise and Avoid Dark Patterns on Social MediaThomas Mildner, Daniel Fidel, Evropi Stefanidi, Pawel W. Wozniak et al.CHI 2025 · 13 citations
- Inaccessible and Deceptive: Examining Experiences of Deceptive Design with People Who Use Visual Accessibility TechnologyAaleyah Lewis, Jesse J. Martinez, Maitraye Das, James FogartyCHI 2025 · 8 citations
- Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human OversightJingyu Tang, Chaoran Chen, Jiawen Li, Zhiping Zhang et al.CHI 2026 · 4 citations
- The Manipulative Power of Voice Characteristics: Investigating Deceptive Patterns in Mandarin Chinese Female Synthetic SpeechShuning Zhang, Han Chen, Yabo Wang, Yiqun Xu et al.UbiComp 2025 · 4 citations
- Does My Chatbot Have an Agenda? Understanding Human and AI Agency in Human-Human-like Chatbot InteractionBhada Yun, Evgenia Taranova, April Yi WangCHI 2026 · 3 citations
Builds on17
- What Makes a Dark Pattern... Dark?: Design Attributes, Normative Considerations, and Measurement MethodsArunesh Mathur, Mihir Kshirsagar, Jonathan R. MayerCHI 2021 · 327 citations
- UI Dark Patterns and Where to Find Them: A Study on Mobile Applications and User PerceptionLinda Di Geronimo, Larissa Braz, Enrico Fregnan, Fabio Palomba et al.CHI 2020 · 262 citations
- Understanding the Benefits and Challenges of Deploying Conversational AI Leveraging Large Language Models for Public Health InterventionEunkyung Jo, Daniel A. Epstein, Hyunhoon Jung, Young-Ho KimCHI 2023 · 167 citations
- Heuristic Evaluation of Conversational AgentsRaina Langevin, Ross J. Lordon, Thi Avrahami, Benjamin R. Cowan et al.CHI 2021 · 159 citations
- Enabling Conversational Interaction with Mobile UI using Large Language ModelsBryan Wang, Gang Li, Yang LiCHI 2023 · 149 citations
Related papers
- When Designers Meet GenAI: Understanding the Role of Prompt-to-Design Generators in Privacy Dark PatternsJingzhou Ye, Zhaojie Hu, Yao Li, Xueqiang WangS&P 2026
- Foody Talk: Exploring Opportunities for Conversational Food JournalingLucas M. Silva, Xi Lu, Emily X. Liang, Daniel A. EpsteinCHI 2025 · 9 citations
- Navigating the Gray: Design Practitioners' Perceptions Toward the Implementation of Privacy Dark PatternsLeah Zhang-Kennedy, Maxwell Keleher, Michaela ValiquetteCSCW 2024 · 24 citations
- "It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational AgentsZhiping Zhang, Michelle Jia, Hao-Ping (Hank) Lee, Bingsheng Yao et al.CHI 2024 · 92 citations
- The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language ModelsYike Shi, Qing Xiao, Qing Hu, Hong Shen et al.CHI 2026 · 7 citations
