IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction

Inna Lin, Ashish Sharma, Christopher Rytting, Adam Miner, Jina Suh, Tim Althoff


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 28% 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 be grounded in psychology theory. Through a randomized trial of 86 participants, we find that IMBUE’s simulation-only variant significantly improves participants’ self-efficacy (up to 17%) and reduces negative emotions (up to 25%). With IMBUE’s additional just-in-time feedback, participants demonstrate 17% improvement in skill mastery, along with greater enhancements in self-efficacy (27% more) and reduction of negative emotions (16% more) compared to simulation-only. The improvement in skill mastery is the only measure that is transferred to new and more difficult situations; situation-specific training is necessary for improving self-efficacy and emotion reduction.
Anthology ID:
2024.acl-long.47
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
810–840
Language:
URL:
https://aclanthology.org/2024.acl-long.47
DOI:
10.18653/v1/2024.acl-long.47
Bibkey:
Cite (ACL):
Inna Lin, Ashish Sharma, Christopher Rytting, Adam Miner, Jina Suh, and Tim Althoff. 2024. IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 810–840, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction (Lin et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.47.pdf