Generative AI (GenAI) image tools are increasingly integrated into design workflows, prompting HCI research on their interaction methods and interfaces. We reviewed 37 such tools, including 28 HCI research systems and nine commercial systems (2022–July 2025), using three analytical frameworks: interaction methods, creative processes, and tool functionalities. We found that text prompts remain the dominant input method, while visual and attribute-based inputs—particularly in academic tools—are gaining traction and are often combined with text for refinement. Commercial systems emphasize parameter control, whereas academic tools focus on semantic attributes and visual organization. Most tools support ideation and exploration, but provide limited support for refinement and evaluation. Based on these findings, we identify nine design opportunities, including advanced visual interaction, simplified parameter control, precision editing, direct manipulation, workflow integration, default settings that support rapid exploration, and user guidance for later stages. We contribute a framework for analyzing GenAI interfaces and actionable directions for designing more usable, creativity-supportive GenAI image systems.

Generative AI (GenAI) systems are inherently non-deterministic, producing varied outputs even for identical inputs. While this variability is central to their appeal, it challenges established HCI evaluation practices that typically assume consistent and predictable system behavior. Designing controlled lab studies under such conditions therefore remains a key methodological challenge. We present a reflective multi-case analysis of four lab-based user studies with GenAI-integrated prototypes, spanning conversational in-car assistant systems and image generation tools for design workflows. Through cross-case reflection and thematic analysis across all study phases, we identify five methodological challenges and propose eighteen practice-oriented recommendations, organized into five guidelines. These challenges represent methodological constructs that are either amplified, redefined, or newly introduced by GenAI’s stochastic nature: (C1) reliance on familiar interaction patterns, (C2) fidelity–control trade-offs, (C3) feedback and trust, (C4) gaps in usability evaluation, and (C5) interpretive ambiguity between interface and system issues. Our guidelines address these challenges through strategies such as reframing onboarding to help participants manage unpredictability, extending evaluation with constructs such as trust and intent alignment, and logging system events, including hallucinations and latency, to support transparent analysis. This work contributes (1) a methodological reflection on how GenAI’s stochastic nature unsettles lab-based HCI evaluation and (2) eighteen recommendations that help researchers design more transparent, robust, and comparable studies of GenAI systems in controlled settings.

Generative AI (GenAI) image tools are increasingly used in design practice, enabling rapid ideation but offering limited support for refinement tasks such as adjusting layout, scale, or visual attributes. While text prompts and inpainting allow localized edits, they often remain inefficient or ambiguous for precise, in-context, and iterative refinement—motivating the exploration of alternative methods. This work examines how pen-based scribbles and annotations can enhance GenAI image refinement. A formative study with seven professional designers informed a prototype supporting three input modalities: text-only, visual-only, and combined prompting. A within-subjects study with 30 designers and design students compared these modalities across closed- and open-ended tasks, evaluating expressiveness, efficiency, workload, user experience, iteration, and multimodal strategies. Visual prompts improved clarity and speed for spatial edits while reducing workload, whereas text remained effective for semantic and global changes. The combined modality received the highest overall ratings, enabling complementary use, balancing spatial precision with semantic detail, and supporting smoother iteration. Task-specific preferences also emerged: adding new objects often required both modalities, while moving or modifying elements was typically handled through visual input. This work contributes (1) an empirical comparison of multimodal prompting for GenAI refinement, (2) a prototype integrating scribbles and annotations, and (3) insights into designers’ multimodal strategies to inform future GenAI interfaces that better support refinement in GenAI-supported design workflows.

The opaque nature of many intelligent systems violates established usability principles and thus presents a challenge for human-computer interaction. Research in the field therefore highlights the need for transparency, scrutability, intelligibility, interpretability and explainability, among others. While all of these terms carry a vision of supporting users in understanding intelligent systems, the underlying notions and assumptions about users and their interaction with the system often remain unclear. We review the literature in HCI through the lens of implied user questions to synthesise a conceptual framework integrating user mindsets, user involvement, and knowledge outcomes to reveal, differentiate and classify current notions in prior work. This framework aims to resolve conceptual ambiguity in the field and enables researchers to clarify their assumptions and become aware of those made in prior work. We further discuss related aspects such as stakeholders and trust, and also provide material to apply our framework in practice (e.g., ideation/design sessions). We thus hope to advance and structure the dialogue on supporting users in understanding intelligent systems.

We present an in-depth analysis of the impact of multi-word suggestion choices from a neural language model on user behaviour regarding input and text composition in email writing. Our study for the first time compares different numbers of parallel suggestions, and use by native and non-native English writers, to explore a trade-off of “efficiency vs ideation”, emerging from recent literature. We built a text editor prototype with a neural language model (GPT-2), refined in a prestudy with 30 people. In an online study (N=156), people composed emails in four conditions (0/1/3/6 parallel suggestions). Our results reveal (1) benefits for ideation, and costs for efficiency, when suggesting multiple phrases; (2) that non-native speakers benefit more from more suggestions; and (3) further insights into behaviour patterns. We discuss implications for research, the design of interactive suggestion systems, and the vision of supporting writers with AI instead of replacing them.

We present a dialogue elicitation study to assess how users envision conversations with a perfect voice assistant (VA). In an online survey, N=205 participants were prompted with everyday scenarios, and wrote the lines of both user and VA in dialogues that they imagined as perfect. We analysed the dialogues with text analytics and qualitative analysis, including number of words and turns, social aspects of conversation, implied VA capabilities, and the influence of user personality. The majority envisioned dialogues with a VA that is interactive and not purely functional; it is smart, proactive, and has knowledge about the user. Attitudes diverged regarding the assistant’s role as well as it expressing humour and opinions. An exploratory analysis suggested a relationship with personality for these aspects, but correlations were low overall. We discuss implications for research and design of future VAs, underlining the vision of enabling conversational UIs, rather than single command “Q&As”.

Unintended consequences of deployed AI systems fueled the call for more interpretability in AI systems. Often explainable AI (XAI) systems provide users with simplifying local explanations for individual predictions but leave it up to them to construct a global understanding of the model behavior. In this work, we examine if non-technical users of XAI fall for an illusion of explanatory depth when interpreting additive local explanations. We applied a mixed methods approach consisting of a moderated study with 40 participants and an unmoderated study with 107 crowd workers using a spreadsheet-like explanation interface based on the SHAP framework. We observed what non-technical users do to form their mental models of global AI model behavior from local explanations and how their perception of understanding decreases when it is examined.

The opaque nature of many intelligent systems violates established usability principles and thus presents a challenge for human-computer interaction. Research in the field therefore highlights the need for transparency, scrutability, intelligibility, interpretability and explainability, among others. While all of these terms carry a vision of supporting users in understanding intelligent systems, the underlying notions and assumptions about users and their interaction with the system often remain unclear.

This reflection paper takes the 25th IUI conference milestone as an opportunity to analyse in detail the understanding of intelligence in the community: Despite the focus on intelligent UIs, it has remained elusive what exactly renders an interactive system or user interface "intelligent", also in the fields of HCI and AI at large. We follow a bottom-up approach to analyse the emergent meaning of intelligence in the IUI community: In particular, we apply text analysis to extract all occurrences of "intelligent" in all IUI proceedings. We manually review these with regard to three main questions: 1) What is deemed intelligent? 2) How (else) is it characterised? and 3) What capabilities are attributed to an intelligent entity? We discuss the community's emerging implicit perspective on characteristics of intelligence in intelligent user interfaces and conclude with ideas for stating one's own understanding of intelligence more explicitly.

Autonomous vehicles are complex systems that may behave in unexpected ways. From the drivers’ perspective, this can cause stress and lower trust and acceptance of autonomous driving. Prior work has shown that explanation of system behavior can mitigate these negative effects. Nevertheless, it remains unclear in which situations drivers actually need an explanation and what kind of interaction is relevant to them. Using thematic analysis of real-world experience reports, we first identified 17 situations in which a vehicle behaved unexpectedly. We then conducted a think-aloud study (N = 26) in a driving simulator to validate these situations and enrich them with qualitative insights about drivers’ need for explanation. We identified six categories to describe the main concerns and topics during unexpected driving behavior (emotion and evaluation, interpretation and reason, vehicle capability, interaction, future driving prediction and explanation request times). Based on these categories, we suggest design implications for autonomous vehicles, in particular related to collaboration insights, user mental models and explanation requests.

The complex nature of intelligent systems motivates work on supporting users during interaction, for example, through explanations. However, as of yet, there is little empirical evidence in regard to specific problems users face when applying such systems in everyday situations. This article contributes a novel method and analysis to investigate such problems as reported by users: We analysed 45,448 reviews of four apps on the Google Play Store (Facebook, Netflix, Google Maps, and Google Assistant) with sentiment analysis and topic modelling to reveal problems during interaction that can be attributed to the apps’ algorithmic decision-making. We enriched this data with users’ coping and support strategies through a follow-up online survey (N = 286). In particular, we found problems and strategies related to content, algorithm, user choice, and feedback. We discuss corresponding implications for designing user support, highlighting the importance of user control and explanations of output rather than processes.

The complex nature of intelligent systems motivates work on supporting users during interaction, for example through explanations. However, there is yet little empirical evidence on specific problems users face in such systems in everyday use. This paper investigates such problems as reported by users: We analysed 35,448 reviews of three apps on the Google Play Store (Facebook, Netflix and Google Maps) with sentiment analysis and topic modelling to reveal problems during interaction that can be attributed to the apps' algorithmic decision-making. We enriched this data with users' coping and support strategies through a follow-up online survey (N=286). In particular, we found problems and strategies related to content, algorithm, user choice, and feedback. We discuss corresponding implications for designing user support, highlighting the importance of user control and explanations of output, not processes. Our work thus contributes empirical evidence to facilitate understanding of users' everyday problems with intelligent systems.

Empowering people through technology is of increasing concern in the HCI community. However, there are different interpretations of empowerment, which diverge substantially. The same term thus describes an entire spectrum of research endeavours and goals. This conceptual unclarity hinders the development of a meaningful discourse and exchange. To better understand what empowerment means in our community, we reviewed 54 CHI full papers using the terms empower and empowerment. Based on our analysis and informed by prior writings on power and empowerment, we construct a framework that serves as a lens to analyze notions of empowerment in current HCI research. Finally, we discuss the implications of these notions of empowerment on approaches to technology design and offer recommendations for future work. With this analysis, we hope to add structure and terminological clarity to this growing and important facet of HCI research.

Intelligent systems, which are on their way to becoming mainstream in everyday products, make recommendations and decisions for users based on complex computations. Researchers and policy makers increasingly raise concerns regarding the lack of transparency and comprehensibility of these computations from the user perspective. Our aim is to advance existing UI guidelines for more transparency in complex real-world design scenarios involving multiple stakeholders. To this end, we contribute a stage-based participatory process for designing transparent interfaces incorporating perspectives of users, designers, and providers, which we developed and validated with a commercial intelligent fitness coach. With our work, we hope to provide guidance to practitioners and to pave the way for a pragmatic approach to transparency in intelligent systems.

Research has brought forth a variety of authentication systems to mitigate observation attacks. However, there is little work about shoulder surfing situations in the real world. We present the results of a user survey (N=174) in which we investigate actual stories about shoulder surfing on mobile devices from both users and observers. Our analysis indicates that shoulder surfing mainly occurs in an opportunistic, non-malicious way. It usually does not have serious consequences, but evokes negative feelings for both parties, resulting in a variety of coping strategies. Observed data was personal in most cases and ranged from information about interests and hobbies to login data and intimate details about third persons and relationships. Thus, our work contributes evidence for shoulder surfing in the real world and informs implications for the design of privacy protection mechanisms.

We present a similarity metric for Android unlock patterns to quantify the effective password space of user-defined gestures. Our metric is the first of its kind to reflect that users choose patterns based on human intuition and interest in geometric properties of the resulting shapes. Applying our metric to a dataset of 506 user-defined patterns reveals very similar shapes that only differ by simple geometric transformations such as rotation. This shrinks the effective password space by 66% and allows informed guessing attacks. Consequently, we present an approach to subtly nudge users to create more diverse patterns by showing background images and animations during pattern creation. Results from a user study (n = 496) show that applying such countermeasures can significantly increase pattern diversity. We conclude with implications for pattern choices and the design of enrollment processes.