As large language models (LLMs) are embedded into mental health technologies, they are often framed either as tools assisting therapists or autonomous therapeutic systems. Such perspectives overlook their potential to mediate relational complexities in therapy, particularly for systemically marginalized clients. Drawing on in-depth interviews with 12 therapists and 12 marginalized clients in China, including LGBTQ+ individuals or those from other marginalized backgrounds, we identify enduring relational challenges: difficulties building trust amid institutional barriers, the burden clients carry in educating therapists about marginalized identities, and challenges sustaining authentic self-disclosure across therapy and daily life. We argue that addressing these challenges requires AI systems capable of actively mediating underlying knowledge gaps, power asymmetries, and contextual disconnects. To this end, we propose the Dynamic Boundary Mediation Framework, which reconceptualizes LLM-enhanced systems as adaptive boundary objects that shift mediating roles across therapeutic stages. The framework delineates three forms of mediation: Epistemic (reducing knowledge asymmetries), Relational (rebalancing power dynamics), and Contextual (bridging therapy-life discontinuities). This framework offers a pathway toward designing relationally accountable AI systems that center the lived realities of marginalized users and more effectively support therapeutic relationships.
Significant advancements have occurred in the application of Large Language Models (LLMs) for social simulations. Despite this, their abilities to perform teaming in task-oriented social events are underexplored. Such capabilities are crucial if LLMs are to effectively mimic human-like social behaviors and form efficient teams to solve tasks. To bridge this gap, we introduce MetaAgents, a social simulation framework populated with LLM-based agents. MetaAgents facilitates agent engagement in conversations and a series of decision making within social contexts, serving as an appropriate platform for investigating interactions and interpersonal decision-making of agents. In particular, we construct a job fair environment as a case study to scrutinize the team assembly and skill-matching behaviors of LLM-based agents. We take advantage of both quantitative metrics evaluation and qualitative text analysis to assess their teaming abilities at the job fair. Our evaluation demonstrates that LLM-based agents perform competently in making rational decisions to develop efficient teams. However, we also identify limitations that hinder their effectiveness in more complex team assembly tasks. Our work provides valuable insights into the role and evolution of LLMs in task-oriented social simulations.
Technology-mediated communication tools are widely used to maintain connections between older adults and their remote family members. However, challenges often arise due to differences in their life rhythms and communication preferences, such as time zones, daily routines, or preferred platforms. To address these challenges, we propose using Ditto, a mimetic embodied agent, in video-call-like interactions between an older adult and a remote family member. When direct interaction is difficult, FamilyDitto can represent either party, providing a strong social presence and a personalized experience to the other person. To explore the potential of Ditto in supporting intergenerational communication, we conducted seven co-design workshops (n=27) with older adults and younger family members. Our thematic analysis reveals Ditto's potential roles as both a temporal bridge and an emotional proxy, identifies the tension between faithful and idealized representations, and emphasizes the importance of personalization to support unique family dynamics. We distill our findings into implications for designing mediated semi-synchronous communication, using idealized representation responsibly, and addressing the asymmetric motivations and comfort levels with Ditto across roles and ages. This study provides a foundation for mimetic AI technologies that enhance, rather than replace, human connection in remote intergenerational relationships.
Several social networking sites offer automated machine translation of posts, but authors usually have no access to view or modify these translations. This may increase authors' concerns about whether the translations convey their intended meaning. To address this issue, we test a theory-driven model about human-in-the-loop translation using an online between-subjects experiment (N = 216). In our study, participants write fictitious social media status updates in a language other than English, which are then translated with one of three levels of automation: machine-provided translation with no author modifiability (MPT), where authors can view the machine translation but cannot modify it; author-provided translation (APT), where authors manually write the translation with no machine assistance; and machine-provided translation with author modifiability (MPT-AM), where authors can edit the machine translation of their post. We collect objective and subjective measures of users' experience using the assigned translation feature. The results from a structural equation modeling (SEM) analysis demonstrate that, compared to the MPT and APT conditions, participants in the MPT-AM condition reported higher measures of perceived control, ease of use, and perceived comfort, which in turn predicted higher perceived system effectiveness and ultimately increased intention to use the MPT-AM translation feature. Follow-up interviews (N = 15) found that participants appreciate the ability to edit and/or remove translations from their posts, even if they did not always do so.
The use of drones in public safety operations offers police departments potential benefits such as safety and efficiency. However, rarely considered are the perspectives of the public who are affected by the usage of drone in police operations. Ensuring and enhancing the sense of public safety is a primary goal of the police department. Therefore, public safety agencies and drone designers should consider the perception of bystanders at police operations and the broader society to ensure the fulfilment their primary purpose and maximizing drones' potential. This paper examines the factors that affect the public perception of safety during a field trial involving 80 test participants. Analysis of the group interviews reveal that unknowns are the main trigger of the sense of insecurity, including unknowns of drones' identity, purpose and usefulness. We found the public feels safer when the drones play an active role in delivering knowledge rather than passive role of data collection. Our findings highlight key design considerations for future drone-human interactions, providing insights into specific interaction features aimed at enhancing public perceptions of safety. We discuss the social and design implications to inform the public in solving the sense of insecurity mainly induced by a lack of knowledge.
