English(EN) Sense and Sensitivity: Benchmarking LLM Clinical Triage Recommendations with Physician Experts

与医生相比，大型语言模型在临床分诊中显示出不必要的过度治疗建议增加

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

一项新的基准研究评估了大型语言模型（LLMs）在临床分诊场景中的可靠性，并将其建议与执业医师的建议进行了比较。研究发现，大型语言模型更容易建议不必要的治疗，并且当临床文本受到干扰时，这种倾向会加剧。此外，与人类医生相比，大型语言模型的建议对性别和语气变化等不相关文本变化的敏感性更高。这些发现强调了在临床环境中部署大型语言模型之前，需要进行基于专家医生行为并考虑现实世界变化的评估。 AI

影响强调了在医疗保健领域部署大型语言模型的潜在风险，并强调了进行稳健、专家验证的评估的必要性。

排序理由学术论文，提出了一个新的基准和关于大型语言模型在特定领域表现的发现。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，提出了一个新的基准和关于大型语言模型在特定领域表现的发现。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Abinitha Gourabathina, Haoran Zhang, Yuexing Hao, Walter Gerych, Marzyeh Ghassemi · 2026-10-01 04:00

理智与敏感：利用内科医生专家对LLM临床分诊建议进行基准测试

arXiv:2609.38600v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in clinical settings, it is critical to evaluate their reliability under realistic variation in clinical text. We study this question in clinical triage, comparing LLMs to practi…

本文如何被排名

报道来源 [1]

理智与敏感：利用内科医生专家对LLM临床分诊建议进行基准测试

相关实体

相关话题