Misinformation can spread rapidly in everyday conversation, where pausing to verify is not always possible. We envision a wearable system that bridges the timing gap between hearing a claim and forming a judgment. It uses ambient listening to detect verifiable claims, performs rapid web verification, and provides a subtle haptic nudge with a glanceable overview. A controlled study (N=34) simulated this approach and tested against a no-support baseline. Results show that instant, body-integrated feedback significantly improved real-time truth discernment and increased verification activity compared to unsupported fact-checking. However, it also introduced over-reliance when the system made errors, i.e. failed to flag false claims or flagged true claims as false. We contribute empirical evidence of improved discernment alongside insights into trust, effort, and user–system tensions in verification wearables.

Given the growing prevalence of fake information, including increasingly realistic AI-generated news, there is an urgent need to train people to better evaluate and detect misinformation. While interactions with AI have been shown to durably reduce people’s beliefs in false information, it is unclear whether these interactions also teach people the skills to discern false information themselves. We conducted a month-long study where 67 participants classified news headline-image pairs as real or fake, discussed their assessments with an AI system, followed by an unassisted evaluation of unseen news items to measure accuracy before, during, and after AI assistance. While AI assistance produced immediate improvements during AI-assisted sessions (+21% average), participants’ unassisted performance on new items declined significantly by 15.3% in week 4 compared to week 0. These results indicate that while AI may help immediately, it may ultimately degrade long-term misinformation detection abilities.

Everyday conversations are more than exchanges of words—they reveal how people think, react, and adapt across situations. Through our speech we reveal the cognitive patterns that shape our behavior over time. Yet much of these patterns remains implicit: people operate through recurring heuristics and habits—some helpful, some limiting, many unnoticed. However, identifying such patterns requires self awareness that humans struggle with—and that current user modeling systems, often fragmented and narrowly tailored to specific tasks, fail to capture. Recognizing these patterns can enable user support systems to go beyond reactive assistance towards anticipatory support. We present Mind Mapper, an always-on wearable AI system that mines behavioral patterns from everyday real-life conversations. Mind Mapper employs a multi-stage LLM pipeline to generate, refine, and evaluate human-readable behavioral patterns. In a field study with 12 participants capturing over 700 hours of real-life conversational data, Mind Mapper generated behavioral patterns that participants consistently rated as accurate, unique, and helpful for reflection and behavior change. We further illustrate how such behavioral pattern modeling might enable new forms of human-AI interaction—anticipating user behavior through proactive interventions, adaptive content delivery, cognitive reframing, and behavioral simulation. Our results show the potential of always-on wearable systems with LLM-driven user models to support new forms of cognitively scaffolding, context-aware human-AI interactions.

CHI ’25, Yokohama, Japan

With the rapid development of advanced machine learning methods for spatial reconstruction, it becomes important to understand the psychological and emotional impacts of such technologies on autobiographical memories. In a within-subjects study, we found that allowing users to walk through old spaces reconstructed from their videos significantly enhances their sense of traveling into past memories, increases the vividness of those memories, and boosts their emotional intensity compared to simply viewing videos of the same past events. These findings highlight that, regardless of the technological advancements, the immersive experience of VR can profoundly affect memory phenomenology and emotional engagement. As systems enabling immersive memory reconstruction become more ubiquitous, it is crucial to critically examine their effects on human cognition and perception of reality.

Fostering students’ interests in learning is considered to have many positive downstream effects. Large language models have opened up new horizons for generating content tuned to one’s interests, yet it is unclear in what ways and to what extent this customization could have positive effects on learning. To explore this novel dimension, we conducted a between-subjects online study (n=272) featuring different variations of a generative AI vocabulary learning app that enables users to personalize their learning examples. Participants were randomly assigned to control (sentence sourced from pre-existing text) or experimental conditions (generated sentence or short story based on users’ text input). While we did not observe a difference in learning performance between the conditions, the analysis revealed that generative AI-driven context personalization positively affected learning motivation. We discuss how these results relate to previous findings and underscore their significance for the emerging field of using generative AI for personalized learning.

Critical thinking is an essential human skill. Despite the importance of critical thinking, research reveals that our reasoning ability suffers from personal biases and cognitive resource limitations, leading to potentially dangerous outcomes. This paper presents the novel idea of AI-framed Questioning that turns information relevant to the AI classification into questions to actively engage users’ thinking and scaffold their reasoning process. We conducted a study with 204 participants comparing the effects of AI-framed Questioning on a critical thinking task; discernment of logical validity of socially divisive statements. Our results show that compared to no feedback and even causal AI explanations of an always correct system, AI-framed Questioning significantly increase human discernment of logically flawed statements. Our experiment exemplifies a future style of Human-AI co-reasoning system, where the AI becomes a critical thinking stimulator rather than an information teller.

Every human culture has developed practices and rituals associated with remembering people of the past - be it for mourning, cultural preservation, or learning about historical events. In this paper, we present the concept of “Living Memories”: interactive digital mementos that are created from journals, letters and data that an individual have left behind. Like an interactive photograph, living memories can be talked to and asked questions, making accessing the knowledge, attitudes and past experiences of a person easily accessible. To demonstrate our concept, we created an AI-based system for generating living memories from any data source and implemented living memories of the three historical figures “Leonardo Da Vinci”, “Murasaki Shikibu”, and “Captain Robert Scott”. As a second key contribution, we present a novel metrics scheme for evaluating the accuracy of living memory architectures and show the accuracy of our pipeline to improve over baselines. Finally, we compare the user experience and learning effects of interacting with the living memory of Leonardo Da Vinci to reading his journal. Our results show that interacting with the living memory, in addition to simply reading a journal, increases learning effectiveness and motivation to learn about the character.

Remote social interactions suffer from a loss of nonverbal cues used to build affiliation and connection. We propose the use of novel sensory channels for sharing social cues from interoceptive data through wearable devices that simulate the breathing and heartbeat patterns of another person, known to be linked to emotional perception and affect. We conducted a study with 16 participants testing the sharing of either heart rate or breathing rate through haptic or audio sensations. Participants experienced these sensations while watching videos of narrators describing personal experiences. We assessed the subjects’ feelings of affiliation and synchrony toward a narrator through surveys, interviews, and correlated physiological data. Our findings show that sensory devices that transfer interoceptive sensations, especially those below the level of conscious perception, can have a positive impact on feelings of connectedness. This has implications for the application of physiological channels in remote interactions to improve social connection.

This paper presents the results of a study with 134 participants to explore the effects of learning from an AI-generated virtual instructor that resembles a person one likes or admires. Given the important role instructors play in shaping learning experiences, as well as the recent surge in demand for online education, we investigate the potential for AI-generated instructors to motivate learning. Recent advances in generative AI have made it easy to create virtual instructors based on the likeness of a present-day, historical or fictional person, thereby enabling customization of video instructors based on the material, context and student. We found that while greater degrees of liking and admiration do not result in increased test scores, they can significantly improve students’ motivation towards learning, foster more positive emotions, and boost their appraisal of the AI-generated instructor as serving as an effective instructor.