Pai 的 AI 雷达

生信医疗

今天：Beyond Accuracy（arXiv:2609），Misaligned Clinical Risk（arXiv:2609）。并行还有 Why AlphaFold Didn't。

日期
2026/10/15
今日条目
103
当前类目
3
往期2026/10/15
全部103编码代理6Agent与工具10个人助理7模型与评测34创作成片14开发与开源11产品接入21
领域机器人具身6硬件边缘1生信医疗3法律合规2金融2安全治理2行业观察5创业者1
#01

Beyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs

arXiv:2609.32807v2 Announce Type: replace Abstract: Clinical LLM evaluation often emphasizes answer accuracy; however, accuracy alone does not test counterfactual consistency or demographic robustness. We evaluated six LLMs on 150 MedQA USMLE questions using two automated perturb

推荐理由Beyond Accuracy: Counterfactual：arXiv:2609.32807v2 Announce Type: replace Abstract: Clinical LLM evaluation often。
模型与评测生信医疗arXiv cs.AI 官方
arxiv.org打开原文
#02

Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models

arXiv:2609.23999v3 Announce Type: replace-cross Abstract: How large language models (LLMs) integrate patient risk with clinical cost tradeoffs remains poorly understood. We investigated how four open-weight LLMs (Qwen-2.5-7B/32B and Llama-3.1-8B/70B) internally represent cost tra

推荐理由Misaligned Clinical Risk Classification：arXiv:2609.23999v3 Announce Type: replace-cross Abstract: How large language models。
模型与评测生信医疗arXiv cs.AI 官方
arxiv.org打开原文
#03

Why AlphaFold Didn't Solve Protein Folding — Pushmeet Kohli, Google DeepMind & Sal Candido, Biohub

From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding , Google DeepMind’s Pushmeet Kohli and Biohub’s Sal Candido are rethinking what it takes to build AI that truly understands biology. In this special panel moderated by Brandon Anderson , they explor

推荐理由Why AlphaFold Didn't Solve Protein：From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding。
创作成片生信医疗Latent Space
latent.space打开原文