On the Step Length Confounding in LLM Reasoning Data Selection
在LLM推理数据选择中的步长混淆问题
Bing Wang, Rui Miao, Chen Shen, Shaotian Yan, Kaiyuan Liu, Ximing Li, Xiaosong Yuan, Sinan Fan, Jun Zhang, Jieping Ye
机构
*
College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院)
;
Key Laboratory of Symbolic Computation and Knowledge Engineering, MoE, Jilin University(吉林大学符号计算与知识工程教育部重点实验室)
;
Alibaba Cloud Computing(阿里云)
;
School of Artificial Intelligence, Jilin University(吉林大学人工智能学院)
;
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
;
Department of Mathematics, University of Michigan(密歇根大学数学系)
;
RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能研究中心)
ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding
ChemVLR:在化学视觉语言理解中优先考虑推理
Xuanle Zhao, Xinyuan Cai, Xiang Cheng, Xiuyi Chen, Bo Xu
机构
*
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所复杂系统认知与决策智能重点实验室)
;
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
CommentsThis version is withdrawn to consolidate the submission under the corresponding author's primary account. The most recent and maintained version of this work can be found at arXiv:2603.09246
A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP
一种通过多任务提示蒸馏与分解的参数高效迁移学习方法用于临床NLP
Cheng Peng, Mengxian Lyu, Ziyi Chen, Yonghui Wu
机构
*
Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida(佛罗里达大学医学院健康结果与生物医学信息学系)
;
Cancer Informatics Shared Resource, University of Florida Health Cancer Center(佛罗里达大学健康癌症中心癌症信息学共享资源)
Comments9 pages, 5 figures. Accepted to workshop on AI and Partial Differential Equations, Foundation Models for Science: Real-World Impact and Science-First Design, Machine Learning for Genomics Explorations, and Generative and Experimental Perspectives for Biomolecular Design at ICLR 2026