Learning therapeutic counseling involves significant role-play experience with mock patients, with current manual training methods providing only intermittent granular feedback. We seek to accelerate and optimize counselor training by providing frequent, detailed feedback to trainees as they interact with a simulated patient. Our first application domain involves training motivational interviewing skills for counselors. Motivational interviewing is a collaborative counseling style in which patients are guided to talk about changing their behavior, with empathetic counseling an essential ingredient. We developed and evaluated an LLM-powered training system that features a simulated patient and visualizations of turn-by-turn performance feedback tailored to the needs of counselors learning motivational interviewing. We conducted an evaluation study with professional and student counselors, demonstrating high usability and satisfaction with the system. We present design implications for the development of automated systems that train users in counseling skills and their generalizability to other types of social skills training.

The proliferation of Large Language Models and Intelligent Virtual Agents acting as psychotherapists offer expanded mental healthcare access.However, their deployment has led to serious harms due to a lack of methods to evaluate nuanced therapeutic risks.Current evaluation techniques lack the sensitivity to detect subtle changes in patient cognition and behavior during therapy sessions that may lead to subsequent decompensation.We introduce a risk ontology for the evaluation of conversational AI psychotherapists.Developed via literature review, expert interviews, and alignment with clinical criteria (DSM-5) and assessment tools (NEQ, UE-ATR), the ontology provides a structured approach to assessing patient harm.

We introduce the concept of “empathic grounding” in conversational agents as an extension of Clark’s conceptualization of grounding in conversation in which the grounding criterion includes listener empathy for the speaker’s affective state. Empathic grounding is generally required whenever the speaker’s emotions are foregrounded and can make the grounding process more efficient and reliable by communicating both propositional and affective understanding. Both speaker expressions of affect and listener empathic grounding can be multimodal, including facial expressions and other nonverbal displays. Thus, models of empathic grounding for embodied agents should be multimodal to facilitate natural and efficient communication. We describe a multimodal model that takes as input user speech and facial expression to generate multimodal grounding moves for a listening agent using a large language model. We also describe a testbed to evaluate approaches to empathic grounding, in which a humanoid robot interviews a user about a past episode of pain and then has the user rate their perception of the robot’s empathy. We compare our proposed model to one that only generates non-affective grounding cues in a between-subjects experiment. Findings demonstrate that empathic grounding increases user perceptions of empathy, understanding, emotional intelligence, and trust. Our work highlights the role of emotion awareness and multimodality in generating appropriate grounding moves for conversational agents.

We introduce a novel application of large language models (LLMs) in developing a virtual counselor capable of conducting motivational interviewing (MI) for alcohol use counseling. Access to effective counseling remains limited, particularly for substance abuse, and virtual agents offer a promising solution by leveraging LLM capabilities to simulate nuanced communication techniques inherent in MI. Our approach combines prompt engineering and integration into a user-friendly virtual platform to facilitate realistic, empathetic interactions. We evaluate the effectiveness of our virtual agent through a series of studies focusing on replicating MI techniques and human counselor dialog. Initial findings suggest that our LLM-powered virtual agent matches human counselors’ empathetic and adaptive conversational skills, presenting a significant step forward in virtual health counseling and providing insights into the design and implementation of LLM-based therapeutic interactions.

Parental permission is required for medical care for children, and decisions may be made without incorporating children's views, even for adolescents. We explore the impact of including adolescents in virtual agent-based multiparty health counseling to promote Human Papillomavirus (HPV) vaccination. The agent is designed to encourage HPV vaccination for children aged 9-12 by engaging co-present parent/adolescent dyads in an online interaction. Several techniques are incorporated, including HPV education, motivational interviewing, persuasion, modeling, and enablement, to address parents' intent to vaccinate their children. We conduct a between-subjects randomized study comparing a version of the agent exclusively for the parent, to one that includes the adolescent in the conversation and incorporates the child's views in counseling strategies. We measure pre- and post-intervention changes in intent to vaccinate, vaccination hesitancy, and knowledge in both the parent and the adolescent, hypothesizing greater improvements in these measures when the adolescent is included in the conversation. We also examine the satisfaction, engagement, and comfort of the parent/child interactions with the virtual agent. We found significant pre-post increases in parent intent to vaccinate their adolescent for both versions of the agent. Our work provides insights into the effectiveness of the virtual agent in promoting HPV vaccination, the impact of child participation on healthcare decision-making, and the user experience of multi-party interaction with the virtual agent.