The Promises and Perils of using LLMs for Effective Public ServicesGovernments are the primary providers of essential public services and are responsible for delivering them effectively. In high-stakes decision-making domains such as child welfare (CW), agencies must protect children without unnecessarily prolonging a family’s engagement with the system. With growing optimism around AI, governments are pushing for its integration but concerns regarding feasibility and harms remain. Through collaborations with a large Canadian CW agency, we examined how LocalLLM and BERTopic models can track CW case progress. We demonstrate how the tools can potentially assist workers in opportunistically addressing gaps in their work by signaling case progress/deviations. And yet, we also show how they fail to detect case trajectories that require discretionary judgments grounded in social work training, areas where practitioners would actually want support to pre-emptively address substantive case concerns. We also provide a roadmap of future participatory directions to co-design language tools for/with the public sector.2026EMErina Seh-Young Moon et al.University of TorontoHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationParticipatory DesignCHI
"When We're Looking at the Robot, We See Each Other": A Comparison of Robotic, Mirror-Based, and Hybrid Interventions for Stranger InteractionEye contact between strangers, even fleeting, can spark interaction and foster connection, happiness, and belonging. Yet in public spaces, such encounters are often suppressed by “civil inattention,” with many people absorbed in their phones. We explore how reconfiguring the ambient environment with MirrorBot, a mobile robot with adaptive mirrors, can encourage social encounters by subtly redirecting glances. By shifting reflections between self- and mutual recognition, MirrorBot invites serendipitous eye contact, shared awareness, and low-stakes engagement. In a controlled 2×2 between-subjects study with 90 participants (45 dyads) across four conditions (MirrorBot, Bot-only, Mirror-only, and control), we found that MirrorBot led participants to initiate conversation more often, feel greater closeness and togetherness, and have more enjoyable interactions. Our findings position robots not only as social agents but as socio-spatial interfaces that choreograph sight lines and shared attention in physical space, opening new possibilities for technologies that cultivate human connection in public life.2026SGSerena Ge Guo et al.University of Wisconsin-MadisonSocial Robot InteractionPhysical-Digital Hybrid InteractionSmart Cities & Urban SensingCHI
Trauma-Informed Digital Evidence Collection: A Design Inquiry into Evidence Practices for Technology-Facilitated Abuse in Intimate Partner ViolenceTechnology-facilitated abuse (TFA) is a widespread and harmful dimension of interpersonal violence. Documenting TFA can unlock mitigative actions for survivors such as legal orders of protection, but existing documentation tools are insufficient. This paper considers whether a trauma-informed design approach could yield more effective methods for documenting TFA and how, concretely, to approach trauma-informed digital evidence collection. Toward this goal, we use trauma-informed methods to design a new tool, Sherloc, that helps identify and document TFA within tech clinic interventions. We evaluated Sherloc in feedback sessions with legal experts, then in a small pilot program in the U.S. From our design inquiry, we present novel guidelines for trauma-informed digital evidence collection. We call on HCI researchers to build on our work to envision trauma-informed methods of documenting TFA.2026SSSophie Stephenson et al.University of Wisconsin-MadisonTechnology Ethics & Critical HCIOnline Harassment & Counter-ToolsCHI
How Well Can 3D Accessibility Guidelines Support XR Development? An Interview Study with XR Practitioners in IndustryWhile accessibility (a11y) guidelines exist for 3D games and virtual worlds, their applicability to extended reality (XR)'s unique interaction paradigms (e.g., spatial tracking, kinesthetic interactions) remains unexplored. XR practitioners need practical guidance to successfully implement a11y guidelines under real-world constraints. We present the first evaluation of existing 3D a11y guidelines applied to XR development through semi-structured interviews with 25 XR practitioners across diverse organization contexts. We assessed 20 commonly-agreed a11y guidelines from six major resources across visual, motor, cognitive, speech, and hearing domains, comparing practitioners' development practices against guideline applicability to XR. Our investigation reveals that guidelines can be highly effective when designed as transformation catalysts rather than compliance checklists, but fundamental mismatches exist between existing 3D guidelines and XR requirements, creating both implementation barriers and design gaps. This work provides foundational insights towards developing a11y guidelines and support tools that address XR's distinct characteristics.2026DKDaniel Killough et al.University of Wisconsin-MadisonVisual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)Universal & Inclusive DesignImmersion & Presence ResearchCHI
PlaceWeave: Understanding Place Through Social Video Narratives and Graph-Enhanced Local KnowledgePeople visiting or moving to a new city often struggle to understand local vibes and everyday routines. Short-form videos on TikTok capture these local stories, but people still have to jump between chatbots, maps, and apps to turn them into concrete plans. We introduce PlaceWeave, a human-centered trip-planning system that foregrounds a place's ''localness''. PlaceWeave builds a place knowledge graph from TikTok videos and uses it to ground all AI features: the conversational assistant, localness attributes on the map, and the route planner all draw on graph evidence. The interface combines an interactive map, an evidence-backed Insights Panel, and tools for organizing discoveries and composing itineraries in a single linked workspace. We validate the attributes and run a within-subjects study with 18 participants, comparing PlaceWeave to a baseline using separate chat, map, video, and canvas tools. PlaceWeave helps people create more local-feeling plans, better understand neighborhood character and trade-offs, and avoid fragmented workflows. We show how localness-aware, graph-grounded AI can support more community-sensitive placemaking technologies.2026ZGZihan Gao et al.University of Wisconsin-MadisonExploratory Search & Information SeekingKnowledge Graph & Semantic SearchSmart Cities & Urban SensingCHI
Creativity from Surprise: Bridging the Gap Between Fashion Designers' Inspiration Work and AI Creative Support ToolsAdvances in Generative AI (GenAI) enable unexpected creation in visual images. In fashion design, this capability has intensified demand for creativity support tools where fast-paced trends challenge fixation and drive exploration of novel creative directions. While prior work has explored interfaces that align designer intent with GenAI outputs, we still lack an empirical understanding of how fashion designers define, seek, and utilize AI-generated surprise as a valuable resource and actionable design direction rather than random noise. We address this gap through a qualitative study combining semi-structured interviews with 20 fashion professionals and a design workshop with 12 graduate students. We conceptualized surprise as a strategy that can be designed into GenAI-powered visualization tools to support traceable exploration, contextual grounding, and controllable variation across ideation stages. This work (1) reframes surprise as a designable mechanism or resource for co-creative interaction, (2) provides empirical insights into how fashion designers can utilize AI-generated surprise in the early stage of design, and (3) translates these insights into actionable guidance for building GenAI-driven visualization tools for fashion and related creative domains from a human-centered AI perspective.2026YJYu Jin et al.Ulsan National Institute of Science and Technology (UNIST)Generative AI (Text, Image, Music, Video)Creative Collaboration & Feedback SystemsGraphic Design & Typography ToolsCHI
Co-Designing Environment-Based Strategies with Neurodivergent Individuals for Sensory-Inclusive Dental Visit ExperiencesDental clinics can be challenging sensory environments, creating discomfort and stress, especially for neurodivergent individuals with Sensory Processing Disorder. Interactive environmental systems offer potential to transform these spaces, providing adaptable, sensory-inclusive experiences. However, the design space for environment-based interventions in dental settings remains largely unexplored. To address this, we conducted in-depth, 2-hour co-design sessions with 13 neurodivergent participants to explore environment-based strategies for meeting diverse sensory needs. We identified five core design goals for inclusive dental environments: experience transformation, distraction, exposure management, restoration, and social facilitation. Our technology-agnostic design catalogue can inform multiple implementation approaches, including projection mapping, ambient displays, and responsive physical elements. We contribute design patterns for interactive environmental systems, methodological insights for participatory design with neurodivergent communities, and demonstrate how tangible materials serve as proxies for environmental interventions, with implications for Augmented Reality system design. This study advances inclusive design practices and highlights co-designing with neurodivergent individuals.2026SGSerena Ge Guo et al.University of Wisconsin-MadisonCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Inclusive DesignTangible Interaction in EducationCHI
Not Seeing the Whole Picture: Challenges and Opportunities in Using AI for Co-Making Physical, DIY-AT for People with Visual ImpairmentsExisting assistive technologies (AT) often adopt a one-size-fits-all approach, overlooking the diverse needs of people with visual impairments (PVI). Do-it-yourself AT (DIY-AT) toolkits offer one path toward customization, but most remain limited—targeting co-design with engineers or requiring programming expertise. Non-professionals with disabilities, including PVI, also face barriers such as inaccessible tools, lack of confidence, and insufficient technical knowledge. These gaps highlight the need for prototyping technologies that enable PVI to directly make their own AT. Building on emerging evidence that large language models (LLMs) can serve not only as visual aids but also as co-design partners, we present an exploratory study of how LLM-based AI can support PVI in the tangible DIY-AT co-making process. Our findings surface key challenges and design opportunities: the need for greater spatial and visual support, strategies for mitigating novel AI errors, and implications for designing more accessible AI-assisted prototypes.2026BKBen Kosa et al.University of Wisconsin--MadisonElectrical Muscle Stimulation (EMS)Generative AI (Text, Image, Music, Video)Explainable AI (XAI)CHI
NaviNote: Enabling In-situ Spatial Annotation Authoring to Support Exploration and Navigation for Blind and Low Vision PeopleGPS and smartphones enable users to place location-based annotations, capturing rich environmental context. Previous research demonstrates that blind and low vision (BLV) people can use annotations to explore unfamiliar areas. However, current commercial systems allowing BLV users to create annotations have never been evaluated, and current GPS-based systems can deviate several meters. Motivated by high-accuracy visual positioning technology, we first conducted a formative study with 24 BLV participants to envision a more accurate and inclusive annotation system. Surprisingly, many participants viewed the high-accuracy technology not just as an annotation system but also as a tool for precise last-few-meters navigation. Guided by participant feedback, we developed NaviNote, which combines vision-based high-precision localization with an agentic architecture to enable voice-based annotation authoring and navigation. Evaluating NaviNote with 18 BLV participants showed that it significantly improved navigation performance and supported users in understanding and annotating their surroundings. Based on these findings, we discuss design considerations for future accessible annotation authoring systems.2026RCRuijia Chen et al.University of Wisconsin-MadisonVisual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)Deaf & Hard-of-Hearing Support (Captions, Sign Language, Vibration)Context-Aware ComputingCHI
Beyond Access: Contextualizing the Benefits of Broadband through Contributor Dynamics on WikipediaBroadband infrastructure is often assumed to reduce informational disparities by expanding access to digital platforms. Yet less is understood about how broadband shapes participation in peer production communities, where knowledge is collectively created and maintained. Using spatial regression models, we examine how broadband coverage influences who contributes and how participation patterns shift in geo-tagged Wikipedia edits across U.S. counties. We find that broadband expansion is strongly associated with increased contributions from local casual and regular editors while reducing reliance on bot-driven activity. However, contributions remain highly concentrated, as prolific editors continue to dominate production. Moreover, we uncover spatial spillover effects, where broadband gains in one county decrease participation in neighboring areas, revealing competitive dynamics in peer production. These findings challenge the assumption that access alone fosters equity, showing that broadband reshapes but does not evenly redistribute editorial influence, with implications for infrastructure policy, platform design, and sustaining inclusive peer production.2026YYYaxuan Yin et al.University of Wisconsin-MadisonCommunity Collaboration & WikipediaCommunity Engagement & Civic TechnologyHCI in Public Health Crises (e.g., COVID-19)CHI
Supporting Money Management among Adults with Down Syndrome: A Multi-Technology Probe StudyFinancial decision-making is critical to adult autonomy, yet many adults with Down syndrome (AwDS) have limited opportunities or support to develop money management skills, often receiving allowances while caregivers oversee financial obligations. To better understand the experiences AwDS have with budgeting and their support preferences, we designed and prototyped three cash-based budgeting technology probes: a gamified tablet application, a tablet-based augmented reality application, and a custom tangible device. Seven AwDS used all three prototypes to complete simplified money management tasks. Across probes, modality tradeoffs shaped engagement and checking: gamification increased interest but encouraged rushing; AR reduced arithmetic but encouraged users to trust the system’s output and skip verification; tangible controls supported participation yet introduced coordination challenges. Error recovery relied on brief, situated prompts linking screen and cash, shaped by prior budgeting/technology experience. These findings point to three design implications: (1) surface budgeting as a stimulating multi-goal puzzle, not just a sequence of steps; (2) design error recovery that connects screen state and real money; (3) support interdependent use without collapsing autonomy.2026HJHailey L Johnson et al.University of WisconsinSpecial Education TechnologyTangible User Interface DesignBehavior Change & Reflection TechnologyCHI
Robot-Assisted Group Tours for Blind PeopleGroup interactions are essential to social functioning, yet effective engagement relies on the ability to recognize and interpret visual cues, making such engagement a significant challenge for blind people. In this paper, we investigate how a mobile robot can support group interactions for blind people. We used the scenario of a guided tour with mixed-visual groups involving blind and sighted visitors. Based on insights from an interview study with blind people (n=5) and museum experts (n=5), we designed and prototyped a robotic system that supported blind visitors to join group tours. We conducted a field study in a science museum where each blind participant (n=8) joined a group tour with one guide and two sighted participants (n=8). Findings indicated users' sense of safety from the robot's navigational support, concerns in the group participation, and preferences for obtaining environmental information. We present design implications for future robotic systems to support blind people's mixed-visual group participation.2026YHYaxin Hu et al.University of Wisconsin-MadisonSocial Robot InteractionRobots in Education & HealthcareVisual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)CHI
RIP Moxie: Lessons for Supporting Emotional Detachment at Product End-of-Life through a Case Study of a Social Companion RobotMeaningful connections formed between people and robots are a key factor in sustaining long-term interaction. Yet while onboarding experiences for social robot products are often carefully designed to cultivate these bonds, offboarding receives far less attention. This imbalance can result in abrupt disruptions in human-robot bonds when products reach end-of-life. In this paper, we examine a case study describing the shutdown of Moxie, a social robot designed to support children's socio-emotional learning. Through a qualitative analysis of the company’s public communications and users’ online reactions to the shutdown, we identify key missed opportunities to prepare and support users throughout the robot’s final interactions. In the absence of a structured offboarding experience, the emotional, technical, and communicative burdens were shifted to parents. Drawing from these findings, we introduce ethical sunsetting recommendations for social robots and offer a reimagined offboarding experience aimed at supporting healthy emotional detachment during product end-of-life.2026BCBengisu Cagiltay et al.University of Wisconsin - MadisonSocial Robot InteractionTechnology in End-of-Life CareDigital Legacy & Online MemorialsCHI
Designing an Affective Mobile Probe to Measure Smile Dynamics in DepressionDepression is a complex disorder for which there is growing interest in identifying objective behavioral markers that measure precise symptoms, such as anhedonia and blunted emotional reactivity. This study explores the feasibility of using smile and smirk expression dynamics, captured through our novel stimulus-based mobile affective probe, as candidate digital biomarkers of depression severity within a large-scale mobile health intervention trial, BeWell. Data from 684 BeWell participants (2,702 observations) are analyzed longitudinally for 16 weeks, comparing their PHQ-8 survey scores with their facial responses to short videos intended to elicit smiles. Mixed-effects models reveal that higher maximum Duchenne smile intensity in reaction to liked stimuli is associated with lower depression scores over time at both within- and between-person levels. We additionally share insights from our tool, including ease of use, perceptions of the stimulus, and technical challenges, which offer considerations for the future development of stimulus-based affect probes in real-world settings.2026NJNelson Hidalgo Julia et al.Massachusetts Institute of TechnologyMental Health Apps & Online Support CommunitiesSleep & Stress MonitoringEmotion-Sensing WearablesCHI
When Metrics Mislead: Parents’ Lived Realities in the Public Safety NetPublic-sector agencies increasingly rely on data and information systems to demonstrate that they “support” families. Yet, the metrics that stand in for support are often misaligned with how they are lived. We draw on interviews with 75 parents involved in the child welfare system (CWS)—an entry point into the broader public safety net—and use an interpretive computational workflow that combines thematic coding, a language model, and multidimensional scaling to examine parents’ accounts of support and needs. We find an ad hoc safety net in which formal services, public assistance, and caseworkers are braided together with kin, peers, and employers, but in fragmented and conditional ways. Parents with robust informal networks are better positioned to appear engaged and receive additional help, while those with few informal supports are more likely to be documented as non-compliant and experience further neglect. These patterns reveal information gaps between sociocentric metrics (e.g.,referrals) and parents’ egocentric outcomes (e.g.,timeliness, feasibility). We discuss implications for designing information systems that use narrative-rich qualitative accounts to uncover latent patterns in how support is experienced by parents in the public safety net.2026DSDevansh Saxena et al.University of Wisconsin-MadisonUser Research Methods (Interviews, Surveys, Observation)Prototyping & User TestingResearch Ethics & Open ScienceCHI
Consent under Constraints: Negotiating Photography and Media Sharing in Institutionalized ChildcareTaking and sharing photos is a routine practice in childcare institutions, used to document children’s learning, communicate with families, and support marketing. These practices are typically regulated through consent forms, the institutional mechanism for authorizing photography and media use. While prior research has examined parents’ photo-taking and sharing, little is known about consent in institutional childcare, where formal policies and non-parental figures (e.g., staff and administrators) shape children’s privacy in distinct ways. To investigate this, we analyzed 42 consent forms and conducted 21 semi-structured interviews with parents, educators, and administrators in U.S.-based childcare institutions. Our findings reveal that consent forms serve as procedural, one-time agreements rather than meaningful safeguards. Parents navigate consent pragmatically amidst structural precarity and power asymmetries, while staff performs the unseen labor of consent enforcement. We conclude with implications for reimagining consent and designing usable institutional mechanisms that support children’s privacy and safety in practice.2026MGMeghna Gupta et al.University of WashingtonCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Universal & Inclusive DesignParticipatory DesignCHI
Reconfiguring the Home: Co-Designing the Future of Adaptive Domestic EnvironmentsAs domestic environments are increasingly required to meet diverse and changing human needs within constrained spaces, physical reconfigurability offers a promising solution. We developed a full-scale, manipulable room prototype as an exploratory co-design instrument, enabling participants to bodily explore and reflect on reconfigurable living spaces. Through 12 sessions with 30 participants involving brainstorming, bodystorming, and interviews, we identified spatial design patterns and elicited perspectives on reconfigurable domestic environments. Our findings contribute a design pattern catalogue for reconfigurable spaces, alongside insights into the lived experience of reconfigurability. We also discuss design principles, three affordance-based design dimensions that capture value tensions: empowering vs. restrictive, utilitarian vs. hedonic, and futuristic vs. practical, as well as lessons from co-design with a room-scale prototype. We demonstrate agile, room-scale prototyping as a methodological approach for spatial HCI research, advancing toward human-computer habitation, where interactive systems become inhabited built environments that support human values, creativity, and autonomy.2026SGSerena Ge Guo et al.University of Wisconsin-MadisonPhysical-Digital Hybrid InteractionSmart Home Interaction DesignAging-in-Place Assistance SystemsCHI
AskNow: An LLM-powered Interactive System for Real-Time Question Answering in Large-Scale ClassroomsIn large-scale classrooms, students often struggle to ask questions due to limited instructor attention and social pressure. Based on findings from a formative study with 24 students and 12 instructors, we designed AskNow, an LLM-powered system that enables students to ask questions and receive real-time, context-aware responses grounded in the ongoing lecture and that allows instructors to view students' questions collectively. We deployed AskNow in three university computer science courses for a week and tested with 117 students. To evaluate AskNow's responses, each instructor rated the perceived correctness and satisfaction of 100 randomly sampled AskNow-generated responses. In addition, we conducted interviews with 24 students and the three instructors to understand their experience with AskNow. We found that AskNow significantly reduced students' perceived time to resolve confusion. Instructors rated AskNow's responses as highly accurate and satisfactory. Instructor and student feedback provided insights into the role of such systems in supporting real-time learning in large lecture settings.2026ZLZiqi Liu et al.University of Wisconsin-MadisonHuman-LLM CollaborationIntelligent Tutoring Systems & Learning AnalyticsCHI
Data-Driven Policymaking: Understanding the Needs and Preferences of Disadvantaged CommunitiesData-driven policymaking has become central in public administration, leveraging datasets to optimize resource allocation and service delivery. Yet this trend raises critical questions about equity, representation, and the inclusion of marginalized communities in data governance. This paper examines the intersection of bureaucratic frameworks, data systems, and community needs, with a focus on disadvantaged groups. Drawing on a nationally representative survey (N = 754) and computational text analysis, we show that low-income respondents and residents of disadvantaged communities are more skeptical of data reliability and transparency, and place greater emphasis on community voice and ethical safeguards than their more advantaged counterparts. Our contribution lies in integrating intersectionality and place-based justice with HCI theories of data governance. We conclude with design recommendations for civic technologies and participatory data infrastructures that create accessible platforms, embed feedback loops, and support co-governance models fostering transparency, trust, and accountability.2026EJEunmi Jeong et al.University of Wisconsin-MadisonAI-Assisted Decision-Making & AutomationAI Ethics, Fairness & AccountabilityPrivacy by Design & User ControlCHI
The Effect of Population Density on Remote Humanitarian Mapping Activities: A Triple-Difference AnalysisThe proliferation of OpenStreetMap (OSM) as a collaborative geographic dataset has been instrumental in addressing data gaps globally. However, disparities in map coverage persist, particularly in economically disadvantaged and disaster-prone regions. The emergence of the Humanitarian OpenStreetMap Team (HOT) in 2010 aimed to bridge these gaps by leveraging the collective efforts of volunteers through platforms like the HOT Tasking Manager. While previous research has highlighted the success of these initiatives in recruiting contributors and expanding map coverage, their implications for existing structural biases remain unclear, potentially hindering the regions benefiting from humanitarian activities. Thus, our study employs the difference-in-difference-in-difference(DDD) approach to empirically examine the pattern between contribution dynamics and population density in project regions involved in humanitarian mapping activities. By further investigating the participation of various levels of contributors in projects with different population densities, we aim to inform better design strategies to align contributor expectations and experiences, fostering more equitable and effective humanitarian mapping efforts.2025YYYaxuan Yin et al.Open Source CommunitiesCSCW