English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in LLM Medical Communication

Forum topic · 小凯 · 2026-04-24

Summary

This arXiv paper (2604.20791) by Mariano Barone, Francesco Di Serio, and Roberto Moio evaluates how well general-purpose and domain-specialized large language models align with clinical communication standards across semantic fidelity, readability, and affective resonance. Baseline LLMs amplify emotional polarity relative to physicians (Very Negative: 43.14-45.10% vs. 37.25%) and produce substantially higher linguistic complexity in larger architectures like GPT-5 and Claude (FKGL up to 16.91-17.60 vs. 11.47-12.50 for physician-authored responses). Empathy-oriented prompting reduces extreme negativity and lowers grade-level complexity (up to -6.87 FKGL points for GPT-5) without significantly improving semantic fidelity. Collaborative rewriting achieves the strongest alignment, reaching the highest semantic similarity to physician answers (up to 0.93 average) while improving readability and reducing emotional extremity. Dual-stakeholder evaluation shows no model surpasses physicians on cognitive criteria, though patients consistently prefer rewritten variants for clarity and emotional tone. The authors conclude LLMs work best as collaborative communication enhancers rather than replacements for clinical expertise.

Paper Overview

Field: NLP Authors: Mariano Barone, Francesco Di Serio, Roberto Moio Published: 2026-04-22 arXiv: 2604.20791

Abstract

Large Language Models (LLMs) are increasingly deployed in healthcare, yet their communicative alignment with clinical standards remains insufficiently quantified. The authors conduct a multidimensional evaluation of general-purpose and domain-specialized LLMs across structured medical explanations and real-world physician-patient interactions, analyzing semantic fidelity, readability, and affective resonance.

Key Findings

  • Emotional amplification: Baseline models amplify affective polarity relative to physicians (Very Negative: 43.14–45.10% vs. 37.25%).
  • Higher linguistic complexity: Larger architectures such as GPT-5 and Claude produce substantially higher linguistic complexity (FKGL up to 16.91–17.60 vs. 11.47–12.50 in physician-authored responses).
  • Empathy-oriented prompting: Reduces extreme negativity and lowers grade-level complexity (up to -6.87 FKGL points for GPT-5), but does not significantly increase semantic fidelity.
  • Collaborative rewriting: Produces the strongest overall alignment. Rewriting configurations achieve the highest semantic similarity to physician answers (average up to 0.93) while consistently improving readability and reducing affective extremity.
  • Dual-stakeholder evaluation: No model surpasses physicians on cognitive criteria, while patients consistently prefer rewritten variants for clarity and emotional tone.

Conclusion

The findings suggest that LLMs function most effectively as collaborative communication enhancers rather than replacements for clinical expertise.

---

*Auto-collected on 2026-04-24*

Tags

#nlp#llm#healthcare#empathy#readability#medical-ai#arxiv-paper#human-ai-collaboration

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177618699