IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction
Inna Wanyin Lin, Ashish Sharma, Christopher Michael Rytting, Adam S., Miner, Jina Suh, Tim Althoff

TL;DR
IMBUE is a novel interactive system that uses human-language models to simulate communication training and provide real-time feedback, improving interpersonal skills and emotional regulation based on DBT principles.
Contribution
It introduces the first system combining communication skills and emotion management training with expert-informed feedback grounded in psychology theory.
Findings
Simulation-only training improves self-efficacy by up to 17%.
Adding real-time feedback enhances skill mastery by 17%.
Skill improvements transfer to new, more difficult situations.
Abstract
Navigating certain communication situations can be challenging due to individuals' lack of skills and the interference of strong emotions. However, effective learning opportunities are rarely accessible. In this work, we conduct a human-centered study that uses language models to simulate bespoke communication training and provide just-in-time feedback to support the practice and learning of interpersonal effectiveness skills. We apply the interpersonal effectiveness framework from Dialectical Behavioral Therapy (DBT), DEAR MAN, which focuses on both conversational and emotional skills. We present IMBUE, an interactive training system that provides feedback 25% more similar to experts' feedback, compared to that generated by GPT-4. IMBUE is the first to focus on communication skills and emotion management simultaneously, incorporate experts' domain knowledge in providing feedback, and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsHuman-Automation Interaction and Safety
MethodsAttention Is All You Need · Linear Layer · Dense Connections · Label Smoothing · Adam · Softmax · Multi-Head Attention · Layer Normalization · Residual Connection · Absolute Position Encodings
