How sensitive do we want AI to be? Socio-communicative competencies of large language models in healthcare

A research study is evaluating the socio-communicative competencies of large language models (LLMs) in a healthcare context. The study uses the HELP-Med dataset, which contains 1800 conversation transcripts between human users seeking medical information and three distinct LLMs (GPT-4o, Llama 3, and Command). This assessment is critical as effective clinical practice relies on strong socio-communicative skills, and LLMs are being considered for various healthcare applications that demand both factual and social competence.

Why it matters

The integration of AI, particularly LLMs, into sensitive domains like healthcare requires a thorough understanding of their capabilities beyond mere factual accuracy. Evaluating socio-communicative competence addresses a fundamental requirement for effective human-computer interaction in clinical settings, directly impacting patient trust, informed decision-making, and the overall quality of care delivery.

Key insights

• The study assesses socio-communicative competencies of LLMs in healthcare.
• It utilizes the HELP-Med dataset, comprising 1800 human-LLM conversation transcripts.
• Three specific LLMs are being evaluated: GPT-4o, Llama 3, and Command.
• LLMs are being considered for healthcare tasks such as patient triaging, report drafting, and medical jargon translation.
• Effective clinical practice is noted to be highly dependent on medical professionals' socio-communicative skills.
• The applications of LLMs in healthcare necessitate both factual and social competence.

Source

arXiv — Computers and Society — https://arxiv.org/abs/2608.07511