Using Emotion Diversification Based on Movie Reviews to Improve the User Experience of Movie Recommender Systems (TIIS)Lansman 等人提出基于电影评论的情绪多样化方法，通过分析用户影评中的情绪分布来改进电影推荐系统的用户体验。2026LLLior Lansman et al.Recommender System UXEmotion Recognition & DetectionIUI
ConverSearch: Supporting Experts in Human Behavior Analysis of Conversational Videos with a Multimodal Scene Search Tool (TIIS)无摘要信息2026RARiku Arakawa et al.Carnegie Mellon UniversityHuman Pose & Activity RecognitionConversational Search & QA SystemsComputational Methods in HCIIUI
Behavioural Indicators of Usability in Visual Analytics Dashboards (TIIS)无摘要信息2026MAMohammed Alhamadi et al.Interactive Data VisualizationVisualization Perception & CognitionIUI
DesignBridge: Bridging Designer Expertise and User Preferences through AI-Enhanced Co-Design for FashionEffective collaboration between designers and users is important for fashion design, which can increase the user acceptance of fashion products and thereby create value. However, it remains an enduring challenge, as traditional designer-centric approaches restrict meaningful user participation, while user-driven methods demand design proficiency, often marginalizing professional creative judgment. Current co-design practices, including workshops and AI-assisted frameworks, struggle with low user engagement, inefficient preference collection, and difficulties in balancing user feedback with design considerations. To address these challenges, we conducted a formative study with designers and users experienced in co-design (N=7), identifying critical challenges for current collaboration between designers and users in the co-design process, and their requirements. Informed by these insights, we introduce DesignBridge, a multi-platform AI-enhanced interactive system that bridges designer expertise and user preferences through three stages: (1) Initial Design Framing, where designers define initial concepts. (2) Preference Expression Collection, where users intuitively articulate preferences via interactive tools. (3) Preference-Integrated Design, where designers use AI-assisted analytics to integrate feedback into cohesive designs. A user study demonstrates that DesignBridge significantly enhances user preference collection and analysis, enabling designers to integrate diverse preferences with professional expertise.2026YSYuheng Shao et al.ShanghaiTech UniversityCreative Collaboration & Feedback SystemsGenerative AI (Text, Image, Music, Video)AI-Assisted Decision-Making & AutomationIUI
Understanding Reader Perception Shifts upon Disclosure of AI AuthorshipAs AI writing support becomes ubiquitous, the question of how disclosing its use affects reader perception remains critical and underexplored. We conducted a controlled study with 261 participants to examine how disclosing varying levels of AI involvement shifts perceptions of the author across six distinct communicative acts. Our analysis of 990 evaluations reveals that disclosure generally erodes perceived trustworthiness, caring, competence, and likability, with the most precipitous declines observed in social and interpersonal writing. A thematic analysis of participant feedback attributes these negative shifts to a perceived loss of human sincerity, diminished authorial effort, and the contextual inappropriateness of AI. Notably, however, we find that higher AI literacy mitigates these negative perceptions, leading to greater tolerance or even appreciation for AI assistance. Our results highlight the nuanced social dynamics of AI-mediated authorship and inform design implications for transparent, context-sensitive writing systems that better preserve trust and authenticity.2026HNHiroki Nakano et al.The University of TokyoGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationAI Ethics, Fairness & AccountabilityIUI
PersonaMail: Learning and Adapting Personal Communication Preferences for Context-Aware Email WritingLLM-assisted writing has seen rapid adoption in interpersonal communication, yet current systems often fail to capture the subtle tones essential for effectiveness. Email writing exemplifies this challenge: effective messages require careful alignment with intent, relationship, and context beyond mere fluency. Through formative studies, we identified three key challenges: articulating nuanced communicative intent, making modifications at multiple levels of granularity, and reusing effective tone strategies across messages. We developed PersonaMail, a system that addresses these gaps through structured communication factor exploration, granular editing controls, and adaptive reuse of successful strategies. Our evaluation compared PersonaMail against standard LLM interfaces, and showed improved efficiency in both immediate and repeated use, alongside higher user satisfaction. We contribute design implications for AI-assisted communication systems that prioritize interpersonal nuance over generic text generation.2026RYRui Yao et al.City University of Hong KongHuman-LLM CollaborationAI-Assisted Writing & Text GenerationAI-Assisted Decision-Making & AutomationIUI
Balancing Flow and Collaboration: Exploring Visual Noise Cancellation in Mixed Reality WorkspaceIn open-plan offices, visual noise from surrounding people and objects can negatively impact both concentration and mood. Mixed Reality (MR) offers a promising approach to address this challenge by reshaping the workspace. In this paper, we first conducted a survey with 50 office workers to examine the impact of visual noise, identifying common sources of distraction and potential mitigation strategies. Considering the necessity of face-to-face communication in office environments, we designed adaptive user interfaces to strike a balance between deep focus and seamless in-situ collaboration. We utilized Virtual Reality (VR) and Diminished Reality (DR) methods to eliminate visual noise and leveraged face orientation along with a distance threshold to determine collaborative intentions. We developed a prototype system and conducted a user study for evaluation. The results indicate that our system can create a tranquil workspace to foster concentration and workplace well-being, while maintaining necessary in-situ collaboration. These findings provide valuable insights for designing future MR-integrated office environments.2026XCXiang Chen et al.Beijing University of Posts and TelecommunicationsMixed Reality WorkspacesImmersion & Presence ResearchIUI
"Same Voice, Different Language": An Exploration of Voice-Cloned Translation to Support Non-Native Speakers in Online MeetingsCross-lingual meetings have become essential for global collaboration, yet current translation technologies often strip away vocal identity — the unique speaker characteristics that convey nuance and social presence. While generic text-to-speech (TTS) provides basic intelligibility, it creates a disconnect between speakers and their translated voices, potentially undermining engagement and comprehension. This paper investigates whether voice cloning technology can bridge this gap by preserving speaker identity in real-time translation. We present a controlled study comparing four voice conditions in meeting interpretation: original speech, gender-neutral TTS, gender-matched TTS, and voice cloning. Through a within-subjects experiment with 45 participants, we demonstrate that voice cloning significantly reduces mental workload ($p < .001$) and enhances user experience across pragmatic quality ($p < .001$), hedonic quality ($p < .001$), and overall satisfaction ($p < .001$) compared to traditional TTS. While original speech maintained advantages in naturalness, voice cloning achieved superior intelligibility, social impression, and user preference. Qualitative analysis revealed that participants valued voice cloning for preserving speaker identity and improving conversation tracking in multi-speaker scenarios. Our findings suggest that identity-preserving translation represents a significant advancement for cross-lingual communication systems, offering both cognitive and social benefits. We conclude with design implications for integrating voice cloning into meeting platforms while addressing ethical considerations around consent and transparency.2026YMYong Ma et al.University of BergenMultilingual & Cross-Cultural Voice InteractionVoice User Interface (VUI) DesignHuman-LLM CollaborationIUI
Improving Human Verification of LLM Reasoning through Interactive Explanation InterfacesThe reasoning capabilities of Large Language Models (LLMs) have led to their increasing employment in several critical applications, particularly education, where they support problem-solving, tutoring, and personalized study. While there are a plethora of works showing the effectiveness of LLMs in generating step-by-step solutions through chain-of-thought (CoT) reasoning on reasoning benchmarks, little is understood about whether the generated CoT is helpful for end-users in improving their ability to comprehend mathematical reasoning problems and detect errors/hallucinations in LLM-generated solutions. To address this gap and contribute to understanding how reasoning can improve human-AI interaction, we present three new interactive reasoning interfaces: interactive CoT (iCoT), interactive Program-of-Thought (iPoT), and interactive Graph (iGraph), and a novel framework that generates the LLM's reasoning from traditional CoT to alternative, interactive formats. Across 125 participants, we found that interactive interfaces significantly improved performance. Specifically, the iGraph interface yielded the highest clarity and error detection rate (85.6 %), followed by iPoT (82.5 %), iCoT (80.6 %), all outperforming standard CoT (73.5 %). Interactive interfaces also led to faster response times, where participants using iGraph were fastest (57.9 secs), compared to iCoT and iPoT (60 secs), and the standard CoT baseline (64.7 secs). Furthermore, participants preferred the iGraph reasoning interface, citing its superior ability to enable users to follow the LLM's reasoning process. We discuss the implications of these results and provide recommendations for the future design of reasoning models. The code and interfaces for this project can be found here: https://github.com/Runtaozhou/Interactive-CoT.2026RZRuntao Zhou et al.University of VirginiaHuman-LLM CollaborationExplainable AI (XAI)Prototyping & User TestingIUI
A Multimodal Investigation of Controllability and Cognitive Load in Interactive Machine LearningInteractive Machine Learning (IML) systems promise to democratize AI by enabling human influence over model behavior, yet the cognitive and behavioral implications of user control remain understudied. We present an investigation of how system controllability affects human factors in IML through the lens of an extensible research platform designed for both pedagogical and research applications. Our system features a toggleable hyperparameter control panel that transforms a streamlined annotation interface into an adjustable learning environment, allowing users to directly manipulate model training dynamics including learning rates, optimizers, and regularization parameters. Through a controlled laboratory study with 46 participants performing Named Entity Recognition (NER) tasks, we used multimodal measurements combining subjective assessments (NASA-TLX), physiological measures (pupil dilation, galvanic skin response), and behavioral metrics to understand the human cost of algorithmic control. Our findings reveal a fundamental tension in IML design: while controllability is often theorized to support agency, it significantly increases cognitive load and task completion time, with users requiring significantly more time when given control options. These findings have implications for the design of human-AI collaborative systems. Our work contributes: (1) a research platform for studying human factors in IML for NLP that includes controllability manipulation and real-time online updates, (2) empirical evidence of the cognitive costs of algorithmic control, and (3) design implications for cognitive sustainability in IML systems. As AI systems become increasingly integrated into professional workflows and educational contexts, understanding these human factors is crucial for creating IML systems that are not only powerful but also cognitively sustainable for long-term use.2026CBCedric Bone et al.Rochester Institute of TechnologyHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationExplainable AI (XAI)IUI
SCSimulator: An Exploratory Visual Analytics Framework for Partner Selection in Supply Chains through LLM-driven Multi-Agent SimulationSupply chains (SCs), complex networks spanning from raw material acquisition to product delivery, with enterprises as interconnected nodes, play a pivotal role in organizational success. However, optimizing SCs remains challenging, particularly in partner selection, a key bottleneck shaped by both competitive and cooperative dynamics. This challenge inherently constitutes a multi-objective dynamic game requiring a synergistic integration of Multi-Criteria Decision-Making (MCDM) and Game Theory (GT). Traditional approaches, grounded in mathematical simplifications and managerial heuristics, often fail to capture real-world intricacies and risk introducing subjective biases. Multi-agent simulation (MAS) offers promise, but prior research has largely relied on fixed, uniform agent logic, limiting practical applicability. Recent advances in Large Language Models (LLMs) create new opportunities to represent complex SC requirements and hybrid game logic. However, challenges persist in modeling dynamic SC relationships, ensuring interpretability, and balancing agent autonomy with expert control. To address these issues, we present SCSimulator, an exploratory visual analytics framework that integrates LLM-driven MAS with human-in-the-loop collaboration for SC partner selection. SCSimulator simulates SC evolution via adaptive network structures and enterprise behaviors, which are visualized via interpretable interfaces. By combining Chain-of-Thought (CoT) reasoning with explainable AI (XAI) techniques, the framework generates multi-faceted, transparent explanations of decision trade-offs. Users can iteratively adjust simulation settings to explore outcomes aligned with their expectations and strategic priorities. Developed through iterative co-design with SC experts and industry managers, SCSimulator serves as a proof-of-concept, offering both methodological contributions and practical insights for future research on SC decision-making and interactive AI-driven analytics. Usage scenarios and a user study further demonstrate the system's effectiveness and usability.2026SGShenghan Gao et al.ShanghaiTech UniversityHuman-LLM CollaborationExplainable AI (XAI)Interactive Data VisualizationIUI
Mapping the Design Space of User Experience for Computer Use AgentsLarge language model (LLM)-based computer use agents execute user commands by interacting with available UI elements, but little is known about how users want to interact with these agents or what design factors matter for their user experience (UX). We conducted a two-phase study to map the UX design space for computer use agents. In Phase 1, we reviewed existing systems to develop a taxonomy of UX considerations, then refined it through interviews with eight UX and AI practitioners. The resulting taxonomy included categories such as user prompts, explainability, user control, and users’ mental models, with corresponding subcategories and example design features. In Phase 2, we ran a Wizard-of-Oz study with 20 participants, where a researcher acted as a web-based computer use agent and probed user reactions during normal, error-prone and risky execution. We used the findings to validate the taxonomy from Phase 1 and deepen our understand of the design space by identifying the connections between design areas and divergence in user needs and scenarios. Our taxonomy and empirical insights provide a map for developers to consider different aspects of user experience in computer use agent design and to situate their designs within users' diverse needs and scenarios.2026RCRuijia Cheng et al.AppleHuman-LLM CollaborationExplainable AI (XAI)AI-Assisted Decision-Making & AutomationIUI
Vulnerability of LLM Outputs to Heuristics-Inducing Prompt StructuresLarge Language Models (LLMs) have become indispensable tools in daily life. Although LLM applications have rapidly expanded across various domains, distorted outputs (specifically, bias and hallucination) are unresolved problems that threaten the reliability of LLM-based artificial intelligence (AI) agents. Focusing on internal mechanisms and social biases, prior research has rarely considered the possibility of distortion-induction even from non-malicious, ordinary prompts with specific input patterns. This study empirically investigates whether LLMs exposed to certain prompt structures can induce biases commonly elicited in humans, namely, representativeness heuristics, anchoring heuristics, and framing heuristics. To this end, we constructed a test set that triggers one of the three heuristics and evaluated the outputs of state-of-the-art LLMs. We further examined the effectiveness of prompt engineering and debiasing interventions. The LLMs continued to produce heuristic-derived biased outputs under certain prompt conditions. Anchoring heuristics were observed at rates significantly above chance, whereas the representativeness and framing heuristics depended on the model and prompt structure. Debiasing interventions notably reduced the representativeness heuristics but exerted limited impact on anchoring and framing heuristics. This study highlights the need for enhanced awareness of vulnerabilities in LLM outputs against particular prompts. It also reveals that typical prompt-engineering strategies offer insufficient protection against such prompt structures. These results will contribute to the safe and effective use of LLMs in human–computer interactions and AI deployment.2026TKToshiki Kuramoto et al.Bridgestone CorporationHuman-LLM CollaborationExplainable AI (XAI)AI Ethics, Fairness & AccountabilityIUI
GuideAI: A Real-time Personalized Learning Solution with Adaptive InterventionsLarge Language Models (LLMs) have emerged as powerful learning tools, but they lack awareness of learners' cognitive and physiological states, limiting their adaptability to the user's learning style. Contemporary learning techniques primarily focus on structured learning paths, knowledge tracing, and generic adaptive testing but fail to address real-time learning challenges driven by cognitive load, attention fluctuations, and engagement levels. Building on findings from a formative user study (N=66), we introduce GuideAI, a multi-modal framework that enhances LLM-driven learning by integrating real-time biosensory feedback including eye gaze tracking, heart rate variability, posture detection, and digital note-taking behavior. GuideAI dynamically adapts learning content and pacing through cognitive optimizations (adjusting complexity based on learning progress markers), physiological interventions (breathing guidance and posture correction), and attention-aware strategies (redirecting focus using gaze analysis). Additionally, GuideAI supports diverse learning modalities, including text-based, image-based, audio-based, and video-based instruction, across varied knowledge domains. A preliminary study (N = 25) assessed GuideAI’s impact on knowledge retention and cognitive load through standardized assessments. The results show statistically significant improvements in both problem-solving capability and recall-based knowledge assessments. Participants also experienced notable reductions in key NASA-TLX measures including mental demand, frustration levels, and effort, while simultaneously reporting enhanced perceived performance. These findings demonstrate GuideAI's potential to bridge the gap between current LLM-based learning systems and individualized learner needs, paving the way for adaptive, cognition-aware education at scale.2026ASAnanya Shukla et al.Plaksha UniversityHuman-LLM CollaborationIntelligent Tutoring Systems & Learning AnalyticsHealth Self-TrackingIUI
NaviEdu: Dual-Path Knowledge Tracing for Detecting Knowledge Shifts and Driving Targeted InterventionsAI-driven education systems seek to infer latent knowledge states and deliver adaptive feedback, enabling personalized learning at scale. Existing approaches span generation- and interaction-based methods as well as feedback-focused systems, but they are largely designed as loosely coupled pipelines. As a result, these methods often lack fine-grained modeling of evolving knowledge states and fail to detect sudden shifts, making it difficult to translate signals into effective personalized interventions. To overcome these issues, we propose NaviEdu, a dual-path causal inference framework where a neural module captures non-linear dynamics and a graph module encodes structured reasoning. he two pathways are coordinated via consistency alignment, Laplacian regularization, and gradient-sensitive updates to keep coherent knowledge representations. A dynamic knowledge graph with feedback further enables a diagnose-intervene-re-diagnose cycle for personalized adaptation. Experiments on three benchmark datasets demonstrate that NaviEdu consistently achieves state-of-the-art AUC and accuracy, with up to 2.2% improvements over strong baselines, while maintaining competitive RMSE and r^2.2026JLjingguang liao et al.South China Normal UniversityIntelligent Tutoring Systems & Learning AnalyticsAI-Assisted Decision-Making & AutomationHuman-LLM CollaborationIUI
Making Absence Visible: The Roles of Reference and Prompting in Recognizing Missing InformationInteractive systems that explain data, or support decision making often emphasize what is present while overlooking what is expected but missing. This presence bias limits users’ ability to form complete mental models of a dataset or situation. Detecting absence depends on expectations about what should be there, yet interfaces rarely help users form such expectations. We present an experimental study examining how reference framing and prompting influence people’s ability to recognize expected but missing categories in datasets. Participants compared distributions across three domains (energy, wealth, and regime) under two reference conditions: Global, presenting a unified population baseline, and Partial, showing several concrete exemplars. Results indicate that absence detection was higher with Partial reference than with Global reference, suggesting that partial, samples-based framing can support expectation formation and absence detection. When participants were prompted to look for what was missing, absence detection rose sharply. We discuss implications for interactive user interfaces and expectation-based visualization design, while considering cognitive trade-offs of reference structures and guided attention.2026HSHagit Ben Shoshan et al.University of HaifaInteractive Data VisualizationUncertainty VisualizationVisualization Perception & CognitionIUI
Embodied Digital Therapists with LLM Personalization for Aphasia Rehabilitation: Characterizing Human-AI Collaboration BoundariesAphasia following stroke affects millions globally, yet rehabilitation remains severely limited by speech therapist shortages. Existing digital systems rely on static video demonstrations, single-modality assessment, and rule-based feedback, failing to address authentic clinical needs. Through formative investigation with five therapists, three patients, and their caregivers, we identified concrete clinical challenges: therapists spending 30-40% of time on repetitive demonstrations, existing tools providing only speech scores without articulatory evaluation, and patients struggling with complex interfaces and monotonous content. To address these challenges, we developed an integrated rehabilitation system combining an embodied digital therapist for Action Observation Therapy, tri-dimensional assessment coordinating speech quality, lip movement accuracy, and semantic understanding, and large language model-driven personalization for content generation and adaptive training. We conducted a proof-of-concept evaluation across two in-situ hospital training sessions with six patients, six caregivers, and three therapists. Results demonstrated substantial efficiency gains, with therapists spending 69-78% less time per patient. Patient acceptance improved 42.6% across sessions, and low digital literacy patients showed steepest gains (+69.0%). However, human intervention remained necessary for 24-30% of session time to provide emotional support. These findings empirically characterize human-AI collaboration boundaries in clinical rehabilitation, revealing both automation's potential to enhance efficiency and bridge digital divides, and the persistent necessity of human therapeutic presence—providing evidence for responsible deployment of AI-assisted healthcare systems.2026MYMengting Yu et al.Southeast UniversityBrain-Computer Interface (BCI) & NeurofeedbackTelemedicine & Remote Patient MonitoringVR Medical Training & RehabilitationIUI
OntoScope: Using a Divergent-Convergent Interaction Framework to Support LLM-based Ontology ScopingAn ontology is a formal, explicit specification of a shared conceptualization that, with problem‑solving and reasoning methods, supports efficient semantic technology development. In ontology engineering, Competency Questions (CQs) capture functional requirements that define an ontology's application domain. Auditing this domain scope with CQs is challenging because in nature, there are no clear domain boundaries, and ontology engineers must then decide which subdomains to cover (horizontal coverage) and how much detail to model (vertical granularity) in an ontology. LLM‑based systems can generate many candidate CQs to guide these decisions, but current tools underuse this potential: they lack support for users' divergent (lateral) and convergent (vertical) thinking in a visualized CQs space organized by coverage and granularity. As a result, users struggle to systematically decide which CQs to adopt, discard, or refine. We propose an interaction framework that fills this gap, demonstrated through OntoScope, an LLM‑based interactive system, and a user study with 15 ontology engineers. To our knowledge, this is the first validated interaction framework with an LLM‑based system that helps ontology engineers audit domain boundaries and unifies fragmented, expert‑driven ontology scoping practices into a coherent, accessible approach. More broadly, it shows how LLM‑based systems can transparently and accountably support a wider range of knowledge‑intensive tasks.2026YZYihang Zhao et al.King's College LondonHuman-LLM CollaborationExplainable AI (XAI)Interactive Data VisualizationIUI
Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic StudyLarge Language Models (LLMs) are increasingly developed for use in complex professional domains, yet little is known about how teams design and evaluate these systems in practice. This paper examines the challenges and trade-offs in LLM development through a 12-week ethnographic study of a team building a pedagogical chatbot. The researcher observed design and evaluation activities and conducted interviews with both developers and domain experts. Analysis revealed four key practices: creating workarounds for data collection, turning to augmentation when expert input was limited, co-developing evaluation criteria with experts, and adopting hybrid expert–developer–LLM evaluation strategies. These practices show how teams made strategic decisions under constraints and demonstrate the central role of domain expertise in shaping the system. Challenges included expert motivation and trust, difficulties structuring participatory design, and questions around ownership and integration of expert knowledge. We propose design opportunities for future LLM development workflows that emphasize AI literacy, transparent consent, and frameworks recognizing evolving expert roles.2026ASAnnalisa Szymanski et al.University of Notre DameHuman-LLM CollaborationParticipatory DesignUser Research Methods (Interviews, Surveys, Observation)IUI
Visual Lyrics: Generating Animated Text for Music Lyric Videos with an Augmented Text EditorAnimated lyric videos transform song lyrics into dynamic visual experiences, offering a powerful medium for artistic expression and audience engagement. However, creating these videos is challenging, requiring expertise in audio, typography, graphic design, and animation, making it inaccessible to novices. To address this challenge, we introduce Visual Lyrics, a proof-of-concept system for generating animated lyric videos controlled with an augmented text editor interface. We examined existing lyric videos to distill a taxonomy and design guidelines, informing the design of Visual Lyrics. Our key insight is a multimodal music analysis pipeline based on the taxonomy and leveraging LLM's strong natural language understanding and code generation capabilities to synthesize creative and semantically meaningful animations. We collected a dataset of over 300 code-driven creative text animations to serve as inspiration for our LLM-driven pipeline, which we open source. In a user study, Visual Lyrics enabled novices to easily create high-quality animated lyric videos with high ratings of enjoyment, inspiration, and exploration.2026DLDavid Chuan-En Lin et al.Carnegie Mellon UniversityAI-Assisted Creative WritingVideo Production & EditingCreative Collaboration & Feedback SystemsIUI