PulseAugur
实时 16:30:53
English(EN) From Documents to Spans: Scalable Supervision for Evidence-Based ICD Coding with LLMs

通过跨度为中心的学习训练的大型语言模型提高了ICD编码的准确性和效率

研究人员开发了一种名为跨度为中心的学习(SCL)的新训练框架,以提高大型语言模型(LLM)在临床文档中分配国际疾病分类(ICD)代码的准确性。该方法侧重于训练LLM识别局部文本跨度中的证据,这比标注整个文档更具可扩展性。SCL增强了LLM在跨度级别的推理能力,并将此能力转移到文档级别的编码中,从而以更低的训练成本显著提高了准确性。 AI

影响 引入了一种更具可扩展性的方法,用于在临床数据上训练LLM,有可能提高诊断编码的准确性和可审计性。

排序理由 这是一篇详细介绍LLM新训练框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

通过跨度为中心的学习训练的大型语言模型提高了ICD编码的准确性和效率

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是一篇详细介绍LLM新训练框架的研究论文。[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, 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
125 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Xu Zhang, Wenxin Ma, Chenxu Wu, Rongsheng Wang, Zhiyang He, Xiaodong Tao, Kun Zhang, S. Kevin Zhou ·

    从文档到跨度:基于LLM的可扩展监督用于基于证据的ICD编码

    arXiv:2603.15270v2 Announce Type: replace Abstract: International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis. Reliable coding requires that each predicted code be supported by…