AReframedChair: Reframing the Empty Chair through Dyadic and Triadic AR-Mediated Self-EmbodimentImmersive technologies are increasingly applied in therapeutic and well-being practices, yet most AR systems focus on dyadic client–avatar interactions and overlook richer therapeutic structures that involve therapists. We introduce AReframedChair, an AR system that reimagines the traditional Empty Chair technique by enabling self-dialogue with a personalized avatar representing one's past or future self. In a between-subjects study with 60 adults, we compared the traditional Empty Chair method with two AR-reframed modes: Dyadic (client–avatar) and Triadic (client–avatar– therapist). Participants' survey responses showed that the Dyadic mode elicited greater positive affect and self-compassion in the past-self scenarios, whereas the Triadic mode produced stronger gains in motivation and reflections in future-self scenarios. Thematic analysis further revealed distinct roles: the Avatar facilitated emotional entry, reassurance, and cognitive reframing, while the Therapists intervened at critical moments to down-regulate intensity, redirect attention, and enhance reflection. These findings open up new design pathways for mental health technologies.2026YLYongming Li et al.Xi'an Jiaotong UniversityVR Medical Training & RehabilitationMental Health Apps & Online Support CommunitiesAffective Feedback & Emotion Regulation InterfacesCHI
Redesigning Educational Videos for Deaf and Hard-of-Hearing LearnersEducational videos are widely used, but accessibility guidelines beyond captions for d/Deaf and Hard-of-Hearing (DHH) learners remain limited. Mayer's multimedia learning theory assumes visual-auditory dual-channel processing, yet DHH learners with limited access to the auditory channel have distinct visual abilities and cognitive demands. This paper introduces motion-driven design ideas to support cognitive processing and improve video-based learning for DHH learners. Through a three-phase study, we identified four key challenges—such as misaligned content and visual overload—and proposed four design ideas that extend multimedia learning theory. We then evaluated these ideas with 16 DHH learners and 6 experts in Deaf education. The results show that motion-driven approaches reduce misalignment, ease visual attention switching, and improve the integration of visual and textual information across video types. For example, guiding visual attention switching minimizes confusion in complex visual contexts, such as programming demonstrations, while using relevant visuals enriches talking-head videos with graphics to clarify abstract ideas in captions. More research is needed to develop these promising ideas into well-defined principles.2026SCSi Chen et al.University of Notre DameDeaf & Hard-of-Hearing Support (Captions, Sign Language, Vibration)K-12 Digital Education ToolsSpecial Education TechnologyCHI
Empowered XR through Generative AI: Balancing Superpowers and RisksThe integration of generative AI with Extended Reality (XR) technologies has unlocked unprecedented capabilities, empowering users with enhanced cognitive, sensory, and environmental control – effectively enabling "superpowers" in immersive digital spaces. This paper explores both the benefits and potential risks. We make two contributions: (i) a synthesized taxonomy of LLM-enabled XR superpowers and their associated risks, and (ii) a set of design guidelines and a forward research agenda derived from that synthesis. We conduct a multi-phase analysis of 135 recent advancements and studies in the field to examine the superpowers granted by these technologies, alongside their associated risks. We categorize the superpowers into internal (cognitive and sensory enhancements) and external (environmental and social manipulations), illustrating how they amplify human abilities in domains such as healthcare, education, and professional training. We then analyze the risks specific to each superpower, revealing critical vulnerabilities in user autonomy, data security, and ethical transparency. This research aims to guide stakeholders in harnessing the potential of XR while mitigating the socio-technical risks of this emerging landscape.2026YTYiliu Tang et al.University of Illinois at Urbana-ChampaignGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationImmersion & Presence ResearchCHI
Inclusive Emotion Technologies: Addressing the Needs of d/Deaf and Hard of Hearing Learners in Video-Based LearningAccessibility efforts for d/Deaf and hard of hearing (DHH) learners in video-based learning have mainly focused on captions and interpreters, with limited attention to learners' emotional awareness--an important yet challenging skill for effective learning. Current emotion technologies are designed to support learners' emotional awareness and social needs; however, little is known about whether and how DHH learners could benefit from these technologies. Our study explores how DHH learners perceive and use emotion data from two collection approaches, self-reported and automatic emotion recognition (AER), in video-based learning. By comparing the use of these technologies between DHH (N=20) and hearing learners (N=20), we identified key differences in their usage and perceptions: 1) DHH learners enhanced their emotional awareness by rewatching the video to self-report their emotions and called for alternative methods for self-reporting emotion, such as using sign language or expressive emoji designs; and 2) while the AER technology could be useful for detecting emotional patterns in learning experiences, DHH learners expressed more concerns about the accuracy and intrusiveness of the AER data. Our findings provide novel design implications for improving the inclusiveness of emotion technologies to support DHH learners, such as leveraging DHH peer learners' emotions to elicit reflections.2025SCSi Chen et al.Accessible & Inclusive TechnologyCSCW
Improving Emotional Support Delivery in Text-Based Community Safety Reporting Using Large Language ModelsEmotional support is a crucial aspect of communication between community members and police dispatchers during incident reporting. However, there is a lack of understanding about how emotional support is delivered through text-based systems, especially in various non-emergency contexts. In this study, we analyzed two years of chat logs comprising 57,114 messages across 8,239 incidents from 130 higher education institutions. Our empirical findings revealed significant variations in emotional support provided by dispatchers, influenced by the type of incident, service time, and a noticeable decline in support over time across multiple organizations. To improve the consistency and quality of emotional support, we developed and implemented a fine-tuned Large Language Model (LLM), named \textit{dispatcherLLM}, designed to suggest replies through simulating human dispatchers' languages with appropriate emotional support. We evaluated \textit{dispatcherLLM} by comparing its generated responses to those of human dispatchers and other off-the-shelf models using real chat messages. Additionally, we conducted a human evaluation to assess the perceived effectiveness of the support provided by \textit{dispatcherLLM}. This study not only contributes new empirical understandings of emotional support in text-based dispatch systems but also demonstrates the significant potential of generative AI in improving service delivery.2025YLYiren Liu et al.AI Applications for Safety and SupportCSCW
Customizing Generated Signs and Voices of AI Avatars: Deaf-Centric Mixed-Reality Design for Deaf-Hearing CommunicationThis study investigates innovative interaction designs for communication and collaborative learning between learners of mixed hearing and signing abilities, leveraging advancements in mixed reality technologies like Apple Vision Pro and generative AI for animated avatars. Adopting a participatory design approach, we engaged 15 d/Deaf and hard of hearing (DHH) students to brainstorm ideas for an AI avatar with interpreting ability (sign language to English and English to sign language) that would facilitate their face-to-face communication with hearing peers. Participants envisioned the AI avatars to address some issues with human interpreters, such as lack of availability, and provide affordable options to expensive personalized interpreting service. Our findings indicate a range of preferences for integrating the AI avatars with actual human figures of both DHH and hearing communication partners. The participants highlighted the importance of having control over customizing the AI avatar, such as AI-generated signs, voices, facial expressions, and their synchronization for enhanced emotional display in communication. Based on our findings, we propose a suite of design recommendations that balance respecting sign language norms with adherence to hearing social norms. Our study offers insights on improving the authenticity of generative AI in scenarios involving specific, and sometimes unfamiliar, social norms.2025SCSi Chen et al.Deaf and Hard-of-Hearing ResearchCSCW
PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research IdeationGenerating interdisciplinary research ideas requires diverse domain expertise, but access to timely feedback is often limited by the availability of experts. In this paper, we introduce \textit{PersonaFlow}, a novel system designed to provide multiple perspectives by using LLMs to simulate domain-specific experts. Our user studies showed that the new design 1) increased the perceived relevance and creativity of ideated research directions, and 2) promoted users’ critical thinking activities (e.g., \textit{interpretation}, \textit{analysis}, \textit{evaluation}, \textit{inference}, and \textit{self-regulation}), without increasing their perceived cognitive load. Moreover, users’ ability to customize expert profiles significantly improved their sense of agency, which can potentially mitigate their over-reliance on AI. This work contributes to the design of intelligent systems that augment creativity and collaboration, and provides design implications of using customizable AI-simulated personas in domains within and beyond research ideation.2025YLYiren Liu et al.Generative AI (Text, Image, Music, Video)Human-LLM CollaborationExplainable AI (XAI)DIS
EyeSee: Enhancing Art Appreciation through Anthropomorphic Interpretations from Multiple PerspectivesArt appreciation serves as a crucial medium for emotional communication and sociocultural dialogue. In the digital era, fostering deep user engagement on online art appreciation platforms remains a challenge. Leveraging large language models (LLMs), we present EyeSee, a system designed to engage users through anthropomorphic characters. We implemented and evaluated three modes--Narrator, Artist, and In-Situ--acting as a third-person narrator, a first-person creator, and first-person created objects, respectively, across two sessions: Narrative and Recommendation. We conducted a within-subject study with 24 participants. In the Narrative session, we found that the In-Situ and Artist modes had higher aesthetic appeal than the Narrator mode, although the Artist mode showed lower perceived usability. Additionally, from the Narrative to the Recommendation session, we found that the user-perceived relatability and believability were sustained, but the user-perceived consistency and stereotypicality changed. Our findings suggest novel implications for anthropomorphic character design in enhancing user engagement.2025YLYongming Li et al.Xi'an Jiaotong University, MOE KLINNS LabAgent Personality & AnthropomorphismGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationCHI
LLM Integration in Extended Reality: A Comprehensive Review of Current Trends, Challenges, and Future PerspectivesThe rapid evolution of Extended Reality (XR) technologies---encompassing Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR)---has paved the way for richer and more immersive user experiences. Concurrently, the emergence of Large Language Models (LLMs), such as GPT-4, has unlocked new opportunities to enhance interactions within XR environments. This paper presents the first comprehensive review addressing the underexplored synergy between XR and LLMs, examining how the integration of these technologies can augment various aspects of human awareness: spatial, situational, social, and self-awareness. By systematically analyzing 135 papers, we synthesize and categorize the research field into seven dimensions: 1) diverse application domains, 2) types of human awareness expanded, 3) interaction paradigms between users and systems, 4) effects of LLMs in XR, 5) practices for effectively integrating LLMs into XR environments, and 6) evaluation metrics. We also discuss remaining challenges and propose future research focusing on ethical awareness.2025YTYiliu Tang et al.University of Illinois at Urbana-Champaign, School of Information SciencesSocial & Collaborative VRImmersion & Presence ResearchHuman-LLM CollaborationCHI
Lessons from Real-World Settings: What Makes It Uniquely Difficult to Design Cognitive Training Programs for Children with Autism Spectrum Disorder and Other Developmental DisabilitiesDespite the prevalence of autism spectrum disorder (ASD) and other developmental disabilities (DD) worldwide, children with ASD and DD face tremendous difficulties receiving support due to physical, financial, and psychological barriers to onsite health and education clinics. As a result, researchers and practitioners have designed software solutions aimed at providing accessible support to meet users’ needs. However, we have limited knowledge of whether these solutions indeed work in real-world settings. To address this gap, we conducted a case study on a cognitive training program called Dubupang, designed by Dubu Inc. From in-depth interviews with multiple stakeholders and field observations of children with ASD and DD, we identify Dubu Inc.’s internal development processes, the critical design issues that emerged through a series of field trials (e.g., instructional design and feedback), and the key implications (e.g., importance of caregivers’ strategic human interventions) for design that better supports both children with ASD and DD and their caregivers.2025HPHyanghee Park et al.University of Illinois Urbana-Champaign, School of Information SciencesCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Special Education TechnologyCHI
EvAlignUX: Advancing UX Evaluation through LLM-Supported Metrics ExplorationEvaluating UX in the context of AI’s complexity, unpredictability, and generative nature presents unique challenges. How can we support HCI researchers to create comprehensive UX evaluation plans? In this paper, we introduce EvAlignUX, a system powered by large language models and grounded in scientific literature, designed to help HCI researchers explore evaluation metrics and their relationship to research outcomes. A user study with 19 HCI scholars showed that EvAlignUX improved the perceived quality and confidence in UX evaluation plans while prompting deeper consideration of research impact and risks. The system enhanced participants' thought processes, leading to the creation of a “UX Question Bank” to guide UX evaluation development. Findings also highlight how researchers’ backgrounds influence their inspiration and concerns about AI over-reliance, pointing to future research on AI’s role in fostering critical thinking. In a world where experience defines impact, we discuss the importance of shifting UX evaluation from a “method-centric” to a “mindset-centric” approach as the key to meaningful and lasting design evaluation.2025QZQingxiao Zheng et al.University of Illinois at Urbana-Champaign, School of Information SciencesHuman-LLM CollaborationExplainable AI (XAI)CHI
Evaluating Non-AI Experts' Interaction with AI: A Case Study In Library ContextPublic libraries in the U.S. are increasingly facing labor shortages, tight budgets, and overworked staff, creating a pressing need for conversational agents to assist patrons. The democratization of generative AI has empowered public service professionals to develop AI agents by leveraging large language models. To understand the needs of non-AI library professionals in creating their own conversational agents, we conducted semi-structured interviews with library professionals (n=11) across the U.S. Insights from these interviews informed the design of EvalignUX, a prototype tool that enables non-AI experts to create conversational agents without coding skills. We then conducted think-aloud sessions and follow-up interviews to evaluate the prototype experience and identify the key evaluation criteria emphasized by library professionals (n=12) when developing conversational agents. Our findings highlight how these professionals perceive the prototype experience and reveal five essential evaluation criteria: interpreting user intent, faithful paraphrasing, proper alignment with authoritative sources, tailoring the tone of voice, and handling unknown answers effectively. These insights provide valuable guidance for designing AI-supported "end-user AI creation tools" in public service domains beyond libraries.2025QZQingxiao Zheng et al.University of Illinois at Urbana-Champaign, School of Information SciencesConversational ChatbotsHuman-LLM CollaborationCHI
ViFeed: Promoting Slow Eating and Food Awareness through Strategic Video Manipulation during Screen-Based DiningGiven the widespread presence of screens during meals, the notion that digital engagement is inherently incompatible with mindfulness. We demonstrate how the strategic design of digital content can enhance two core aspects of mindful eating: slow eating and food awareness. Our research unfolded in three sequential studies: (1). Zoom Eating Study: Contrary to the assumption that video-watching leads to distraction and overeating, this study revealed that subtle video speed manipulations—can promote slower eating (by 15.31%) and controlled food intake (by 9.65%) while maintaining meal satiation and satisfaction. (2). Co-design workshop: Informed the development of ViFeed, a video playback system strategically incorporating subtle speed adjustments and glanceable visual cues. (3). Field Study: A week-long deployment of ViFeed in daily eating demonstrated its efficacy in fostering food awareness, food appreciation, and sustained engagement. By bridging the gap between ideal mindfulness practices and screen-based behaviors, this work offers insights for designing digital-wellbeing interventions that align with, rather than against, existing habits.2025YCYang Chen et al.National University of Singapore, College of Design and EngineeringDiet Tracking & Nutrition ManagementFood Culture & Food InteractionCHI
AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart GlassesUnlike the free exploration of childhood, the demands of daily life reduce our motivation to explore our surroundings, leading to missed opportunities for informal learning. Traditional tools for knowledge acquisition are reactive, relying on user initiative and limiting their ability to uncover hidden interests. Through formative studies, we introduce AiGet, a proactive AI assistant integrated with AR smart glasses, designed to seamlessly embed informal learning into low-demand daily activities (e.g., casual walking and shopping). AiGet analyzes real-time user gaze patterns, environmental context, and user profiles, leveraging large language models to deliver personalized, context-aware knowledge with low disruption to primary tasks. In-lab evaluations and real-world testing, including continued use over multiple days, demonstrate AiGet’s effectiveness in uncovering overlooked yet surprising interests, enhancing primary task enjoyment, reviving curiosity, and deepening connections with the environment. We further propose design guidelines for AI-assisted informal learning, focused on transforming everyday moments into enriching learning experiences.2025RCRunze Cai et al.National University of Singapore, Synteraction Lab, School of ComputingAR Navigation & Context AwarenessGenerative AI (Text, Image, Music, Video)Context-Aware ComputingCHI
From Scores to Careers: Understanding AI’s Role in Supporting Collaborative Family Decision-Making in Chinese College ApplicationsThis study investigates how 18-year-old students, parents, and experts in China utilize artificial intelligence (AI) tools to support decision-making in college applications during college entrance exam- a highly competitive, score-driven, annual national exam. Through 32 interviews, we examine the use of Quark GaoKao, an AI tool that generates college application lists and acceptance probabilities based on exam scores, historical data, preferred locations, etc. Our findings show that AI tools are predominantly used by parents with limited involvement from students, and often focus on immediate exam results, failing to address long-term career goals. We also identify challenges such as misleading AI recommendations, and irresponsible use of AI by third-party consultant agencies. Finally, we offer design insights to better support multi-stakeholders' decision-making in families, especially in the Chinese context, and discuss how emerging AI tools create barriers for families with fewer resources.2025SCSi Chen et al.University of Illinois at Urbana Champaign , School of Information SciencesHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationSTEM Education & Science CommunicationCHI
GlassMail: Towards Personalised Wearable Assistant for On-the-Go Email Creation on Smart GlassesOptical See-through Head-Mounted Displays (OHMDs) offer new opportunities for completing complex information processing tasks on the go. We introduce GlassMail, a Large Language Models (LLMs)-based wearable assistant on OHMDs for mobile email creation. Our formative study identified two challenges of the LLM-based wearable email assistant: (i) achieving efficient and accurate understanding of user intentions, and (ii) ensuring effective information presentation for email processes. Through two empirical studies, we developed a "Single Turn with Optional Clarification" approach for accurate user intention recognition and a "Fade Context with Optional Audio" mode for effective email processing. An observation study then evaluated GlassMail’s feasibility in composing formal and semi-formal emails, supporting the usefulness and effectiveness of GlassMail in simple scenarios and yielding insights into potential future improvements for complex scenarios. We further discuss the design implications for the future development of wearable AI-enabled assistants.2024CZChen Zhou et al.Mid-Air Haptics (Ultrasonic)Human-LLM CollaborationHome Voice Assistant ExperienceDIS
AudioXtend: Assisted Reality Visual Accompaniments for Audiobook Storytelling During Everyday Routine TasksThe rise of multitasking in contemporary lifestyles has positioned audio-first content as an essential medium for information consumption. We present AudioXtend, an approach to augment audiobook experiences during daily tasks by integrating glanceable, AI-generated visuals through optical see-through head-mounted displays (OHMDs). Our initial study showed that these visual augmentations not only preserved users' primary task efficiency but also dramatically enhanced immediate auditory content recall by 33.3% and 7-day recall by 32.7%, alongside a marked improvement in narrative engagement. Through participatory design workshops involving digital arts designers, we crafted a set of design principles for visual augmentations that are attuned to the requirements of multitaskers. Finally, a 3-day take-home field study further revealed new insights for everyday use, underscoring the potential of assisted reality (aR) to enhance heads-up listening and incidental learning experiences.2024FTFelicia Fang-Yi Tan et al.National University of SingaporeAR Navigation & Context AwarenessGenerative AI (Text, Image, Music, Video)CHI
How AI Processing Delays Foster Creativity: Exploring Research Question Co-Creation with an LLM-based AgentDeveloping novel research questions (RQs) often requires extensive literature reviews, especially in interdisciplinary fields. To support RQ development through human-AI co-creation, we leveraged Large Language Models (LLMs) to build an LLM-based agent system named CoQuest. We conducted an experiment with 20 HCI researchers to examine the impact of two interaction designs: breadth-first and depth-first RQ generation. The findings revealed that participants perceived the breadth-first approach as more creative and trustworthy upon task completion. Conversely, during the task, participants considered the depth-first generated RQs as more creative. Additionally, we discovered that AI processing delays allowed users to reflect on multiple RQs simultaneously, leading to a higher quantity of generated RQs and an enhanced sense of control. Our work makes both theoretical and practical contributions by proposing and evaluating a mental model for human-AI co-creation of RQs. We also address potential ethical issues, such as biases and over-reliance on AI, advocating for using the system to improve human research creativity rather than automating scientific inquiry. The system’s source is available at: https://github.com/yiren-liu/coquest.2024YLYiren Liu et al.University of Illinois at Urbana - ChampaignGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationAI Ethics, Fairness & AccountabilityCHI
Towards Inclusive Video Commenting: Introducing Signmaku for the Deaf and Hard-of-HearingPrevious research underscored the potential of danmaku: a text-based commenting feature on videos for engaging hearing audiences. However, many Deaf and hard-of-hearing (DHH) users prioritize American Sign Language (ASL) over English. To improve inclusivity, we introduce Signmaku, a commenting mechanism that uses ASL as a sign language version of danmaku. Through a need-finding study (N=12) and a within-subject experiment (N=20), we evaluated three design styles: real human faces, cartoon-like, and robotic depictions. We found that cartoon signmaku not only provided entertainment but also prompted participants to create and share ASL comments with fewer privacy concerns compared to the other designs. Conversely, the robotic design's limited accuracy in conveying hand movements and facial expressions increased cognitive demands. Realist signmaku elicited the lowest cognitive load and was the easiest to understand among all three types. Our findings offer unique design implications for leveraging generative AI to create signmaku comments, enhancing co-learning experiences for DHH users.2024SCSi Chen et al.University of Illinois Urbana-ChampaignIntelligent Voice Assistants (Alexa, Siri, etc.)Generative AI (Text, Image, Music, Video)Deaf & Hard-of-Hearing Support (Captions, Sign Language, Vibration)CHI
Understanding Safety Risks and Safety Design in Social VR EnvironmentsUnderstanding the emerging safety risks in nuanced social VR spaces and how existing safety features are used is crucial for building safe and inclusive 3D virtual worlds in the future. Prior research on safety risks in social VR is mainly based on interview or survey data of social VR users' experiences and perceptions, which lacks "in-situ observations'' about how people actually react to these risks. In this paper, we aim to understand safety risks and safety design in social VR environments using two empirical studies. In Study 1, we conducted content analysis of 212 YouTube videos and the associated transcripts that document social VR users' first hand experiences of safety risks in social VR environments in the moment (e.g., as victims, attackers, or bystanders). We also investigated viewers' reactions to these risks by analyzing comments to these videos posted online (i.e., spectators). In Study 2, we identified 13 safety features across various social VR platforms and mapped how each existing safety feature in social VR can address the risks identified in Study 1. Our findings call for re-approaching safety risks based on the uniqueness of social VR interaction dynamics and users' multi-modal simulated reactions to such risks. We also propose three safety protection mechanisms for designing future social VR environments: the use of non-player character (NPC) as a safety educator, intuitive gesture-based safety triggers, and improvements for avatar and voice control.2023QZQingxiao Zheng et al.SafetyCSCW