When Traditional Medicine Meets AI: Critical Considerations for AI-Empowered Clinical Support in Traditional MedicineTraditional Medicine (TM) is the oldest healthcare form and has been increasingly adopted as the primary or complementary medical therapy in the world. However, TM’s practical development remains highly challenging. While AI has become powerful in advancing modern medicine, limited attention has been paid to its potential and usage in TM. This study addressed this gap through a probe-based interview study with 16 TM clinicians, examining their experiences, perceptions, and expectations of AI-empowered clinical support systems. Our findings revealed that despite numerous AI-CDS systems, their practical usage in TM settings was still limited. We identified a series of practical challenges when integrating AI-CDS into TM clinical scenarios, largely due to TM’s unique features and the significant data work challenges these features present. We end by critically discussing the potential issues that may arise when integrating AI into practical TM scenarios, and proposing a series of practical recommendations for future studies.2025YSYuling Sun et al.AI-Assisted HealthcareCSCW
"AI Afterlives" as Digital Legacy: Perceptions, Expectations, and ConcernsThe rise of generative AI technology has sparked interest in using digital information to create AI-generated agents as digital legacy. These agents, often referred to as "AI Afterlives", present unique challenges compared to traditional digital legacy. Yet, there is limited human-centered research on "AI Afterlife" as digital legacy, especially from the perspectives of the individuals being represented by these agents. This paper presents a qualitative study examining users' perceptions, expectations, and concerns regarding AI-generated agents as digital legacy. We identify factors shaping people's attitudes, their perceived differences compared with the traditional digital legacy, and concerns they might have in real practices. We also examine the design aspects throughout the life cycle and interaction process. Based on these findings, we situate "AI Afterlife" in digital legacy, and delve into design implications for maintaining identity consistency and balancing intrusiveness and support in "AI Afterlife" as digital legacy.2025YLYing Lei et al.Simon Fraser University, School of Interactive Arts and TechnologyGenerative AI (Text, Image, Music, Video)Online Identity & Self-PresentationCHI
Scaffolded Turns and Logical Conversations: Designing Humanized LLM-Powered Conversational Agents for Hospital Admission InterviewsHospital admission interviews are critical for patient care but strain nurses' capacity due to time constraints and staffing shortages. While LLM-powered conversational agents (CAs) offer automation potential, their rigid sequencing and lack of humanized communication skills risk misunderstandings and incomplete data capture. Through participatory design with clinicians and volunteers, we identified essential communication strategies and developed a novel CA that implements these strategies through: (1) dynamic topic management using graph-based conversation flows, and (2) context-aware scaffolding with few-shot prompt tuning. Technical evaluation on an admission interview dataset showed our system achieving performance comparable to or surpassing human-written ground truth, while outperforming prompt-engineered baselines. A between-subject study (N=44) demonstrated significantly improved user experience and data collection accuracy compared to existing solutions. We contribute a framework for humanizing medical CAs by translating clinician expertise into algorithmic strategies, alongside empirical insights for balancing efficiency and empathy in healthcare interactions, and considerations for generalizability.2025DLDingdong Liu et al.The Hong Kong University of Science and TechnologyConversational ChatbotsHuman-LLM CollaborationCHI
Signaling Human Intentions to Service Robots: Understanding the Use of Social Cues during In-Person ConversationsAs social service robots become commonplace, it is essential for them to effectively interpret human signals, such as verbal, gesture, and eye gaze, when people need to focus on their primary tasks to minimize interruptions and distractions. Toward such a socially acceptable Human-Robot Interaction, we conducted a study (N=24) in an AR-simulated context of a coffee chat. Participants elicited social cues to signal intentions to an anthropomorphic, zoomorphic, grounded technical, or aerial technical robot waiter when they were speakers or listeners. Our findings reveal common patterns of social cues over intentions, the effects of robot morphology on social cue position and conversational role on social cue complexity, and users' rationale in choosing social cues. We offer insights into understanding social cues concerning perceptions of robots, cognitive load, and social context. Additionally, we discuss design considerations on approaching, social cue recognition, and response strategies for future service robots.2025HLHanfang Lyu et al.Hong Kong University of Science and TechnologySocial Robot InteractionHuman-Robot Collaboration (HRC)CHI
Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-MakingTraditional AI-assisted decision-making systems often provide fixed recommendations that users must either accept or reject entirely, limiting meaningful interaction—especially in cases of disagreement. To address this, we introduce Human-AI Deliberation, an approach inspired by human deliberation theories that enables dimension-level opinion elicitation, iterative decision updates, and structured discussions between humans and AI. At the core of this approach is Deliberative AI, an assistant powered by large language models (LLMs) that facilitates flexible, conversational interactions and precise information exchange with domain-specific models. Through a mixed-methods user study, we found that Deliberative AI outperforms traditional explainable AI (XAI) systems by fostering appropriate human reliance and improving task performance. By analyzing participant perceptions, user experience, and open-ended feedback, we highlight key findings, discuss potential concerns, and explore the broader applicability of this approach for future AI-assisted decision-making systems.2025SMShuai Ma et al.The Hong Kong University of Science and TechnologyHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationCHI
DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-DecompositionDecomposition is a fundamental skill in algorithmic programming, requiring learners to break down complex problems into smaller, manageable parts. However, current self-study methods, such as browsing reference solutions or using LLM assistants, often provide excessive or generic assistance that misaligns with learners' decomposition strategies, hindering independent problem-solving and critical thinking. To address this, we introduce Decomposition Box (DBox), an interactive LLM-based system that scaffolds and adapts to learners' personalized construction of a step tree through a "learner-LLM co-decomposition" approach, providing tailored support at an appropriate level. A within-subjects study (N=24) found that compared to the baseline, DBox significantly improved learning gains, cognitive engagement, and critical thinking. Learners also reported a stronger sense of achievement and found the assistance appropriate and helpful for learning. Additionally, we examined DBox's impact on cognitive load, identified usage patterns, and analyzed learners' strategies for managing system errors. We conclude with design implications for future AI-powered tools to better support algorithmic programming education.2025SMShuai Ma et al.The Hong Kong University of Science and TechnologyHuman-LLM CollaborationProgramming Education & Computational ThinkingIntelligent Tutoring Systems & Learning AnalyticsCHI
Towards Feature Engineering with Human and AI’s Knowledge: Understanding Data Science Practitioners' Perceptions in Human&AI-Assisted Feature Engineering DesignAs AI technology continues to advance, the importance of human-AI collaboration becomes increasingly evident, with numerous studies exploring its potential in various fields. One vital field is data science, including feature engineering (FE), where both human ingenuity and AI capabilities play pivotal roles. Despite the existence of AI-generated recommendations for FE, there remains a limited understanding of how to effectively integrate and utilize humans' and AI's knowledge. To address this gap, we design a readily usable prototype, human\&AI-assisted FE in Jupyter notebooks. It harnesses the strengths of humans and AI to provide feature suggestions to users, seamlessly integrating these recommendations into practical workflows. Using the prototype as a research probe, we conducted an exploratory study to gain valuable insights into data science practitioners' perceptions, usage patterns, and their potential needs when presented with feature suggestions from both humans and AI. Through qualitative analysis, we discovered that the "Creator" of the feature (i.e., AI or human) significantly influences users' feature selection, and the semantic clarity of the suggested feature greatly impacts its adoption rate. Furthermore, our findings indicate that users perceive both differences and complementarity between features generated by humans and those generated by AI. Lastly, based on our study results, we derived a set of design recommendations for future human & AI FE design. Our findings unveil vast collaborative potential between humans and AI in the field of FE.2024QZQian Zhu et al.Human-LLM CollaborationAI-Assisted Decision-Making & AutomationComputational Methods in HCIDIS
"Are You Really Sure?'' Understanding the Effects of Human Self-Confidence Calibration in AI-Assisted Decision MakingIn AI-assisted decision-making, it is crucial but challenging for humans to achieve appropriate reliance on AI. This paper approaches this problem from a human-centered perspective, "human self-confidence calibration". We begin by proposing an analytical framework to highlight the importance of calibrated human self-confidence. In our first study, we explore the relationship between human self-confidence appropriateness and reliance appropriateness. Then in our second study, We propose three calibration mechanisms and compare their effects on humans' self-confidence and user experience. Subsequently, our third study investigates the effects of self-confidence calibration on AI-assisted decision-making. Results show that calibrating human self-confidence enhances human-AI team performance and encourages more rational reliance on AI (in some aspects) compared to uncalibrated baselines. Finally, we discuss our main findings and provide implications for designing future AI-assisted decision-making interfaces.2024SMShuai Ma et al.The Hong Kong University of Science and TechnologyExplainable AI (XAI)AI-Assisted Decision-Making & AutomationCHI
Unpacking ICT-supported Social Connections and Support of Late-life Migration: From the Lens of Social ConvoysMigration and aging-related dilemmas have limited the opportunities for late-life migrants to rebuild social connections and access support. While research on migrants has drawn increasing attention in HCI, limited attention has been paid to the increasing number of late-life migrants. This paper reports a qualitative study examining the social connections and support of late-life migrants. In particular, drawing on the social convoy model, we pay specific attention to the dynamic changes of late-life migrants' social convoy, the supporting roles each convoy plays, the functions ICT plays in the process, as well as the encountered challenges and expectations of late-life migrants regarding ICT-supported social convoys. Based on these findings, we deeply discuss the role of the social convoy in supporting more targeted social support for late-life migrants, as well as broader migrant communities. Finally, we offer late-life migrant-oriented design considerations.2024YLYing Lei et al.East China Normal UniversityCommunity Engagement & Civic TechnologyDeveloping Countries & HCI for Development (HCI4D)CHI
Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-MakingExisting research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers. There is a limited understanding of how AI may perform in group decision-making. This paper presents a wizard-of-oz study in which two participants and an AI form a committee to rank three English essays. One novelty of our study is that we adopt a speculative design by endowing AI equal power to humans in group decision-making. We enable the AI to discuss and vote equally with other human members. We find that although the voice of AI is considered valuable, AI still plays a secondary role in the group because it cannot fully follow the dynamics of the discussion and make progressive contributions. Moreover, the divergent opinions of our participants regarding an "equal AI" shed light on the possible future of human-AI relations.2023CZChengbo Zheng et al.Hong Kong University of Science and TechnologyHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationCHI
RetroLens: A Human-AI Collaborative System for Multi-step Retrosynthetic Route PlanningMulti-step retrosynthetic route planning (MRRP) is the core task in synthetic chemistry, in which chemists recursively deconstruct a target molecule to find a set of reactants that make up the target. MRRP is challenging in that the search space is vast, and chemists are often lost in the process. Existing AI models can achieve automatic MRRP fast, but they only work on relatively simple targets, which leaves complex molecules under chemists' expertise. To facilitate MRRP of complex molecules, we proposed a human-AI collaborative system, RetroLens, through a participatory design process. AI can contribute by two approaches: joint action and algorithm-in-the-loop. Deconstruction steps are allocated to chemists or AI based on their capabilities and AI recommends candidate revision steps to fix problems along the way. A within-subjects study (N=18) showed that chemists who used RetroLens reported faster MRRP, broader design space exploration, higher confidence in their planning, and lower cognitive load.2023CSChuhan Shi et al.Hong Kong University of Science and TechnologyAI-Assisted Decision-Making & AutomationCHI
Glancee: An Adaptable System for Instructors to Grasp Student Learning Status in Synchronous Online ClassesSynchronous online learning has become a trend in recent years. However, instructors often face the challenge of inferring audiences' reactions and learning status without seeing their faces in video feeds, which prevents instructors from establishing connections with students. To solve this problem, based on a need-finding survey with 67 college instructors, we propose Glancee, a real-time interactive system with adaptable configurations, sidebar-based visual displays, and comprehensive learning status detection algorithms. Then, we conduct a within-subject user study in which 18 college instructors deliver lectures online with Glancee and two baselines, EngageClass and ZoomOnly. Results show that Glancee can effectively support online teaching and is perceived to be significantly more helpful than the baselines. We further investigate how instructors' emotions, behaviors, attention, cognitive load, and trust are affected during the class. Finally, we offer design recommendations for future online teaching assistant systems.2022SMShuai Ma et al.The Hong Kong University of Science and TechnologyOnline Learning & MOOC PlatformsCollaborative Learning & Peer TeachingCHI