Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasonin

ACL ARR 2025 February Submission6153 Authors

Abstract: The severe shortage of medical doctors limits access to timely and reliable healthcare, leaving millions underserved. Large language models (LLMs) offer a potential solution but struggle in real-world clinical interactions. Their language is often rigid and mechanical, lacking the human-like qualities essential for patient trust. To address these challenges, we propose \textit{Ask Patients with Patience (APP)}, a multi-turn LLM-based medical assistant designed for grounded reasoning and human-centric interaction. APP enhances communication by eliciting user symptoms through empathetic dialogue, significantly improving accessibility and user engagement. It also incorporates Bayesian active learning to ensure reliable and transparent diagnoses. The framework is built on verified medical guidelines from the MSD Manual, ensuring grounded and evidence-based reasoning. To evaluate its performance, we develop a new benchmark that simulates a realistic clinical consultation environment using real-world interview cases. We compare APP against SOTA one-shot and multi-turn LLM baselines. Results show that APP improves diagnostic accuracy, reduces uncertainty, and enhances user experience. By integrating medical expertise with transparent, human-like interaction, APP bridges the gap between AI-driven medical assistance and real-world clinical practice.

Paper Type: Long

Research Area: Human-Centered NLP

Research Area Keywords: human-AI interaction

Languages Studied: English

Submission Number: 6153