English(EN) Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

研究发现AI推理训练损害疾病预测

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-09 01:00

一项新的研究论文挑战了这样一种普遍假设：使用合成推理数据进行监督微调可以提高语言模型在临床预测任务上的性能。在阿尔茨海默病预测方面的实验发现，与仅使用标签进行微调相比，该方法始终会降低性能，即使推理在医学上是准确的。研究表明，叙事合理性与判别性优化之间的冲突可能是原因，并敦促在开发用于高风险医疗应用的语言模型时要谨慎。 AI

影响挑战了基于推理的微调在高风险临床预测中的有效性，表明需要更鲁棒的训练方法。

排序理由该集群包含一篇详细介绍AI模型训练方法实验结果的学术论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Buxin Su, Bingxuan Li, Cheng Qian, Yiwei Wang, Jin Jin, Bingxin Zhao · 2026-06-10 04:00

Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

arXiv:2606.10279v1 Announce Type: new Abstract: Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching models not just what to predict but why. We test this assumption on five-year Alzh…
Hugging Face Daily Papers TIER_1 English(EN) · 2026-06-09 01:00

Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching models not just what to predict but why. We test this assumption on five-year Alzheimer's disease and related dementias (ADRD) pre…

报道来源 [2]

Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

相关实体

相关话题