The growing demand for accessible mental health support requires training more counselors, yet existing approaches remain resource-intensive and difficult to scale. LLMs can realistically simulate patients and generate actionable feedback for training, but their actual impact on novice counselor skill development remains unknown. We developed an LLM-simulated practice and feedback system and conducted a randomized study with 94 novice counselors, comparing practice alone versus practice with feedback. We evaluated behavioral performance, self-efficacy, and qualitative reflections. Results showed the practice-and-feedback group improved in client-centered microskills (reflections, questions), while the practice-alone group showed no improvements. For empathy, the practice-alone group declined over time and performed significantly worse than the feedback group. Qualitative interviews reinforced these findings: feedback helped participants adopt a client-centered listening approach, while practice-alone participants remained solution-oriented. These results suggest LLM-based training systems can promote effective skill development, and combining simulated practice with structured feedback is critical for meaningful improvement.

Support-seekers' self-disclosure of their suffering experiences, thoughts, and feelings in the post can help them get needed peer support in online mental health communities (OMHCs). However, such mental health self-disclosure could be challenging. Images can facilitate the manifestation of relevant experiences and feelings in the text; yet, relevant images are not always available. In this paper, we present a technical prototype named MentalImager and validate in a human evaluation study that it can generate topical- and emotional-relevant images based on the seekers' drafted posts or specified keywords. Two user studies demonstrate that MentalImager not only improves seekers' satisfaction with their self-disclosure in their posts but also invokes support-providers' empathy for the seekers and willingness to offer help. Such improvements are credited to the generated images, which help seekers express their emotions and inspire them to add more details about their experiences and feelings. We report concerns on MentalImager and discuss insights for supporting self-disclosure in OMHCs.

Realistic practice and tailored feedback are key processes for training peer counselors with clinical skills.However, existing mechanisms of providing feedback largely rely on human supervision.Peer counselors often lack mechanisms to receive detailed feedback from experienced mentors, making it difficult for them to support the large number of people with mental health issues who use peer counseling.Our work aims to leverage large language models to provide contextualized and multi-level feedback to empower peer counselors, especially novices, at scale.To achieve this, we co-design with a group of senior psychotherapy supervisors to develop a multi-level feedback taxonomy, and then construct a publicly available dataset with comprehensive feedback annotations of 400 emotional support conversations.We further design a self-improvement method on top of large language models to enhance the automatic generation of feedback.Via qualitative and quantitative evaluation with domain experts, we demonstrate that our method minimizes the risk of potentially harmful and lowquality feedback generation which is desirable in such high-stakes scenarios.

Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills.However, simulating sensitive interactions, such as in the domain of mental health, is challenging.Privacy concerns restrict data access, and collecting expert feedback, although vital, is laborious.To address this, we develop Roleplay-doh, a novel human-LLM collaboration pipeline that elicits qualitative feedback from a domain-expert, which is transformed into a set of principles, or natural language rules, that govern an LLMprompted roleplay.We apply this pipeline to enable senior mental health supporters to create customized AI patients as simulated practice partners for novice counselors.After uncovering issues with basic GPT-4 simulations not adhering to expert-defined principles, we also introduce a novel principle-adherence prompting pipeline which shows a 30% improvement in response quality and principle following for the downstream task.Through a user study with 25 counseling experts, we demonstrate that the pipeline makes it easy and effective to create AI patients that more faithfully resemble real patients, as judged by both creators and third-party counselors.We provide access to the code and data on our project website 1 .

Context-aware applications have the potential to act opportunistically to facilitate human experiences and activities, from reminding us of places to perform personal activities, to identifying coincidental moments to engage in digitally-mediated shared experiences. However, despite the availability of context-detectors and programming frameworks for defining how such applications should trigger, designers lack support for expressing their human concepts of a situation and the experiences and activities they afford (e.g., situations to toss a frisbee) when context-features are made available at the level of locations (e.g., parks). This paper introduces Affinder, a block-based programming environment that supports constructing concept expressions that effectively translate their conceptions of a situation into a machine representation using available context features. During pilot testing, we discovered three bridging challenges that arise when expressing situations that cannot be encoded directly by a single context-feature. To overcome these bridging challenges, Affinder provides designers (1) an unlimited vocabulary search for discovering features they may have forgotten; (2) prompts for reflecting and expanding their concepts of a situation and ideas for foraging for context-features; and (3) simulation and repair tools for identifying and resolving issues with the precision of concept expressions on real use-cases. In a comparison study, we found that Affinder’s core functions helped designers stretch their concepts of how to express a situation, find relevant context-features matching their concepts, and recognize when the concept expression operated differently than intended on real-world cases. These results show that Affinder and tools that support bridging can improve a designer’s ability to express their concepts of a human situation into detectable machine representations—thus pushing the boundaries of how computing systems support our activities in the world.

There is an increasing interest from ML and HCI communities in empowering creators with better generative models and more intuitive interfaces with which to control them. In music, ML researchers have focused on training models capable of generating pieces with increasing long-range structure and musical coherence, while HCI researchers have separately focused on designing steering interfaces that support user control and ownership. In this study, we investigate how developments in both models and user interfaces are important for empowering co-creation where the goal is to create music that communicates particular imagery or ideas (e.g., as is common for other purposeful tasks in music creation like establishing mood or creating accompanying music for another media). Our study is distinguished in that it measures communication through both composer’s self-reported experiences, and how listeners evaluate this communication through the music. In an evaluation study with 26 composers creating 100+ pieces of music and listeners providing 1000+ head-to-head comparisons, we find that more expressive models and more steerable interfaces are important and complementary ways to make a difference in composers communicating through music and supporting their creative empowerment.

While generative deep neural networks (DNNs) have demonstrated their capacity for creating novel musical compositions, less attention has been paid to the challenges and potential of co-creating with these musical AIs, especially for novices. In a needfinding study with a widely used, interactive musical AI, we found that the AI can overwhelm users with the amount of musical content it generates, and frustrate them with its non-deterministic output. To better match co-creation needs, we developed AI-steering tools, consisting of Voice Lanes that restrict content generation to particular voices; Example-Based Sliders to control the similarity of generated content to an existing example; Semantic Sliders to nudge music generation in high-level directions (happy/sad, conventional/surprising); and Multiple Alternatives of generated content to audition and choose from. In a summative study (N=21), we discovered the tools not only increased users' trust, control, comprehension, and sense of collaboration with the AI, but also contributed to a greater sense of self-efficacy and ownership of the composition relative to the AI.

Despite many available social technologies for connecting at a distance, we don't always find opportunities to actively engage in shared experiences and activities with friends and loved ones, even though this kind of interaction is associated with increased social closeness. To better support active engagement in shared experiences and activities while also making it convenient to find opportunities for interacting in this way, our work explores the design of Opportunistic Collective Experiences (OCEs), or social experiences powered by computer programs that identify opportune moments when users share situations across distance and structure shared activities in those situations. To support interacting with, programming, and executing OCEs, we developed Cerebro, a computational platform that consists of a mobile app that supports users? social interaction, an API for expressing the situations and activities that make up the interactional opportunity, and an opportunistic execution engine that checks for interactional opportunities and executes them when possible. Through a 20 day deployment study tested with groups of geographically-distributed college alumni (N=21), we found that OCEs promoted opportunities for active engagement; facilitated interactions that were socially connecting by structuring ways to engage in shared experiences and activities; and made actively engaging easier by identifying situations appropriate for interacting and structuring how to engage in activities in these situations. We contribute to CSCW (1) a novel interaction that facilitates engaging in shared experiences and activities at distance during coincidental moments; and (2) the design of systems to interact with, program, and execute these kinds of interactions.

The introduction of augmented reality technology to iOS and Android enables, for the first time, mainstream smartphones to estimate their own motion in 3D space with high accuracy. For assistive technology researchers, this development presents a potential opportunity. In this spirit, we present our work leveraging these technologies to create a smartphone app to empower people who are visually impaired to more easily navigate indoor environments. Our app, Clew, allows users to record routes and then load them, at any time, providing automatic guidance (using haptic, speech, and sound feedback) along the route. We present our user-centered design process, Clew's system architecture and technical details, and both small and large-scale evaluations of the app. We discuss opportunities, pitfalls, and design guidelines for utilizing augmented reality for orientation and mobility apps. Our work expands the capabilities of technology for orientation and mobility that can be distributed on a mass scale.