Effective communication in serious illness and palliative care is essential but often under-taught due to limited access to training resources like standardized patients. We present PAL (Palliative Assisted Learning-bot), a conversational system that simulates emotionally nuanced patient interactions and delivers structured feedback grounded in an existing empathy-based framework. PAL supports text and voice modalities and is designed to scaffold clinical skill-building through repeated, low-cost practice. Through a mixed-methods study with 17 U.S. medical trainees and clinicians, we explore user engagement with PAL, evaluate usability, and examine design tensions around modalities, emotional realism, and feedback delivery. Participants found PAL helpful for reflection and skill refinement, though some noted limitations in emotional authenticity and the adaptability of feedback. We contribute: (1) empirical evidence that large language models can support palliative communication training; (2) design insights for modality-aware, emotionally sensitive simulation tools; and (3) implications for systems that support emotional labor, cooperative learning, and AI-augmented training in high-stakes care settings.
@article{arxiv.2507.02122,
title = {PAL: Designing Conversational Agents as Scalable, Cooperative Patient Simulators for Palliative-Care Training},
author = {Neil K. R. Sehgal and Hita Kambhamettu and Allen Chang and Andrew Zhu and Lyle Ungar and Sharath Chandra Guntuku},
journal= {arXiv preprint arXiv:2507.02122},
year = {2025}
}