Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering
组合推理深度预测临床AI失败:与电子健康记录问答中Transformer组合性限制一致的实证证据
Sanjay Basu
机构
*
University of California San Francisco(加州大学旧金山分校)
;
Waymark
Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models
基于因果归因的剪枝保留大型语言模型的推理性能
Amogh Sheth, Biruk Assefa, Yi Wen Huang, Andrew Lin, Yuhao Ge
机构
*
Edison Academy Magnet School(爱迪生学院磁石学校)
;
Massachusetts Institute of Technology(麻省理工学院)
;
State University of New York College at Plattsburgh(纽约州立大学普拉茨堡学院)
;
The University of Texas at Austin(德克萨斯大学奥斯汀分校)
;
Independent Researcher(独立研究员)
Comments17 pages, 10 figures. Includes an exact F-test for non-transportability with verified size and power, its precision-whitened generalisation, and a foreign-exchange case where the null hypothesis is known analytically rather than estimated
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
从推理轨迹到可复用模块:理解语言模型推理中的组合泛化
Lingjing Kong, Xin Liu, Guangyi Chen, Martin Q. Ma, Xiangchen Song, Yuekai Sun, Mikhail Yurochkin, Taylor W. Killian, Ruslan Salakhutdinov, Kun Zhang, Eric P. Xing, Zhengzhong Liu
机构
*
Carnegie Mellon University(卡内基梅隆大学)
;
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
Institute of Foundation Models(基础模型研究院)
;
University of Michigan(密歇根大学)
机构
*
School of Artificial Intelligence, Beijing Normal University(北京师范大学人工智能学院)
;
Beijing Key Laboratory of Artificial Intelligence for Education(北京人工智能教育重点实验室)
;
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所)
;
School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院)
;
Department of Computer Science and Technology, Institute for AI, Tsinghua University(清华大学人工智能研究院计算机科学与技术系)
;
Northeastern University(东北大学)
机构
*
College of Artificial Intelligence, Nanjing Agricultural University(南京农业大学人工智能学院)
;
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院)