(CA) Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves

大型语言模型无法可靠地更新临床判断

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-05 04:00

arXiv上发表的一项新研究表明，大型语言模型（LLM）在新的患者证据出现时，难以更新其临床判断。研究人员发现，随着证据的演变，LLM的预测错误常常会增加，并且在应对病情恶化和好转的证据时表现出不对称性。当先验风险增加时，模型也表现出估计值的显著变化，这表明其自身先验信念具有因果影响。提示并未解决这些问题，一种名为“证据验证纵向更新”（EVLU）的新评估方法突显了LLM性能在可靠性和覆盖率之间的权衡。 AI

影响凸显了LLM在临床决策等高风险应用中可靠性方面的关键差距，需要进一步研究鲁棒的信念更新机制。

排序理由该集群包含一篇研究论文，详细介绍了LLM在特定领域局限性方面的新发现。[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: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了LLM在特定领域局限性方面的新发现。[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; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 (CA) · Min Zeng, Rui Zhang · 2026-10-05 04:00

大型语言模型在患者证据演变时，临床判断更新不可靠

arXiv:2610.02684v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly explored for clinical reasoning, but whether they appropriately revise judgments as patient evidence evolves remains unclear. We evaluated longitudinal belief updating using matched inte…

本文如何被排名

报道来源 [1]

大型语言模型在患者证据演变时，临床判断更新不可靠

相关实体

相关话题