AI Chatbots as Professional Service Agents: Developing a Professional Identity

TL;DR

This paper introduces LAPI, a framework for developing AI chatbots with a professional identity in healthcare, enhancing communication quality and aligning responses with professional and ethical standards.

Contribution

The paper presents a novel LAPI framework that guides LLMs to act as professional healthcare agents with aligned communication, using a theory-guided task planning and entropy-based response generation.

Findings

Outperforms baseline methods in fluency, empathy, and patient-centricity.

Effective in generating professional and ethical responses with low uncertainty.

Ablation study confirms the importance of each component in the framework.

Abstract

With the rapid expansion of large language model (LLM) applications, there is an emerging shift in the role of LLM-based AI chatbots from serving merely as general inquiry tools to acting as professional service agents. However, current studies often overlook a critical aspect of professional service agents: the act of communicating in a manner consistent with their professional identities. This is of particular importance in the healthcare sector, where effective communication with patients is essential for achieving professional goals, such as promoting patient well-being by encouraging healthy behaviors. To bridge this gap, we propose LAPI (LLM-based Agent with a Professional Identity), a novel framework for designing professional service agent tailored for medical question-and-answer (Q\&A) services, ensuring alignment with a specific professional identity. Our method includes a theory-guided task planning process that decomposes complex professional tasks into manageable subtasks aligned with professional objectives and a pragmatic entropy method designed to generate professional and ethical responses with low uncertainty. Experiments on various LLMs show that the proposed approach outperforms baseline methods, including few-shot prompting, chain-of-thought prompting, across key metrics such as fluency, naturalness, empathy, patient-centricity, and ROUGE-L scores. Additionally, the ablation study underscores the contribution of each component to the overall effectiveness of the approach.