用大模型无监督分析医患对话中的20种社交信号，提升医疗沟通评估效率。
SocialLM: Social Signal Processing of Patient-Provider Communication using LLMs and Contextual Aggregation
- 通过提示工程在不微调情况下检测20类社交行为
- 不同患者种族和就诊阶段表现差异明显，但集成方法显著提升稳定性
- 适合临床对话分析、医疗质量评估等场景使用
有效医患沟通难以大规模评估。我们检验大语言模型（LLMs）在不进行微调的情况下，能否从临床对话转录文本中追踪20种社交行为。在三种模型族和多种提示策略下，LLMs能可靠检测社交信号，但性能受患者种族和就诊阶段影响。为应对仅限查询接口的约束，我们提出基于群体一致性的加权集成方法，该方法在准确率和稳定性上均优于最佳单个模型，展示了在临床对话中实现可扩展社交信号追踪的实用路径。
原文摘要 · Abstract (English)
Effective patient-provider communication is difficult to assess at scale. We examine whether large language models (LLMs) can track 20 social behaviors from clinical transcripts without fine-tuning. Across three model families and multiple prompting strategies, LLMs reliably detect social signals, though performance varies by patient race and visit segment. To address this variability under query-only API constraints, we introduce an agreement-weighted ensemble using group-level agreement patterns. This approach improves both accuracy and stability over the best individual model, demonstrating a practical pathway for scalable social signal tracking in clinical conversations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。