Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
别停止我:通过耗散黎曼流形力学采样损失极小值
Albert Kjøller Jacobsen, Leo Uhre Jakobsen, Johanna Marie Gegenfurtner, Georgios Arvanitidis
机构
*
Section for Cognitive Systems, Technical University of Denmark(丹麦技术大学认知系统系)
;
Center for Quantum Information Physics, New York University(纽约大学量子信息物理中心)
Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
为何语言模型比人类更不惊讶?测试解析多重性不匹配假说
William Timkey, Brian Dillon, Tal Linzen
机构
*
Department of Linguistics, New York University(纽约大学语言学系)
;
Center for Data Science, New York University(纽约大学数据科学中心)
;
Department of Linguistics, University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校语言学系)
机构
*
Data Sciences and Operations Department, University of Southern California(南加州大学数据科学与运营系)
;
Stern School of Business, New York University(纽约大学斯特恩商学院)
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
DynamicNER: 一种动态、多语言和细粒度的用于基于大语言模型的命名实体识别的数据集
Hanjun Luo, Yingbin Jin, Xinfeng Li, Xuecheng Liu, Ruizhe Chen, Tong Shang, Kun Wang, Qingsong Wen, Zuozhu Liu
机构
*
New York University Abu Dhabi(纽约大学阿布扎赫德分校)
;
Zhejiang University(浙江大学)
;
The Hong Kong Polytechnic University(香港理工大学)
;
Nanyang Technology University(南阳技术大学)
;
University of Electronic Science and Technology of China(电子科技大学)
;
Texas A&M University(德克萨斯大学)
;
Squirrel AI
Prompt Stability Scoring for Text Annotation with Large Language Models
基于大语言模型的文本标注提示稳定性评分
Christopher Barrie, Elli Palaiologou, Petter Törnberg
机构
*
Department of Sociology, New York University(纽约大学社会学系)
;
Independent Researcher(独立研究者)
;
Institute for Logic, Language, and Computation, University of Amsterdam(阿姆斯特丹大学逻辑、语言与计算研究所)