PulseAugur
中
实时 08:37:29
English(EN) Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models

决策模型适配临床智能，准确率达95%

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员通过适配一个基于Qwen 3.5骨干的90亿参数决策模型Clef-Flash，开发了一种新颖的临床智能方法。该模型使用QLoRA的参数高效微调，在Symptom2Disease基准测试上达到了95.42%的诊断准确率。该系统展示了显著的速度提升，每条记录的推理时间不到80毫秒，比生成式LLM基线提高了31倍。此外，还引入了一个新的反事实扰动框架Leave-One-Symptom-Out，用于评估症状级别证据和可解释性。 AI

影响 展示了在临床环境中实现低延迟、可解释AI的潜力，提高了诊断速度和准确性。

排序理由 详细介绍新模型适配和评估的研究论文。[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 →

决策模型适配临床智能，准确率达95%

本文如何被排名

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍新模型适配和评估的研究论文。[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
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]

  1. arXiv cs.AI TIER_1 English(EN) · S. M. Mahbub Uddin Ahmed ·

    迈向System One临床智能：决策基础模型的参数高效微调与反事实可解释性

    arXiv:2610.15029v1 Announce Type: cross Abstract: Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the contextual understanding and latency costs of autoregressive large language models (LLMs…

相关实体

相关话题