Shortcut Learning of Large Language Models in Natural Language Understanding

被引：13
|
作者：
Du, Mengnan [1 ]
He, Fengxiang [2 ]
Zou, Na [3 ]
Tao, Dacheng [4 ]
Hu, Xia [5 ]
机构：
[1] New Jersey Inst Technol, Dept Data Sci, Newark, NJ 07102 USA
[2] Univ Edinburgh, Sch Informat, Edinburgh, Scotland
[3] Texas A&M Univ, Engn Technol & Ind Distribut, College Stn, TX USA
[4] Univ Sydney, Comp Sci, Sydney, Australia
[5] Rice Univ, Comp Sci, Houston, TX USA
来源：
COMMUNICATIONS OF THE ACM | 2024年 / 67卷 / 01期
关键词：
D O I：
10.1145/3596490
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Shortcuts often hinder the robustness of large language models. © 2023 ACM.
引用
收藏
页码：110 / 120
页数：11
相关论文
共 50 条
  • [1] Understanding natural language: Potential application of large language models to ophthalmology
    Yang, Zefeng
    Wang, Deming
    Zhou, Fengqi
    Song, Diping
    Zhang, Yinhang
    Jiang, Jiaxuan
    Kong, Kangjie
    Liu, Xiaoyi
    Qiao, Yu
    Chang, Robert T.
    Han, Ying
    Li, Fei
    Tham, Clement C.
    Zhang, Xiulan
    ASIA-PACIFIC JOURNAL OF OPHTHALMOLOGY, 2024, 13 (04):
  • [2] Reliable Natural Language Understanding with Large Language Models and Answer Set Programming
    Rajasekharan, Abhiramon
    Zeng, Yankai
    Padalkar, Parth
    Gupta, Gopal
    Electronic Proceedings in Theoretical Computer Science, EPTCS, 2023, 385 : 274 - 287
  • [3] Reliable Natural Language Understanding with Large Language Models and Answer Set Programming
    Rajasekharan, Abhiramon
    Zeng, Yankai
    Padalkar, Parth
    Gupta, Gopal
    ELECTRONIC PROCEEDINGS IN THEORETICAL COMPUTER SCIENCE, 2023, (385): : 274 - 287
  • [4] The Journey of Language Models in Understanding Natural Language
    Liu, Yuanrui
    Zhou, Jingping
    Sang, Guobiao
    Huang, Ruilong
    Zhao, Xinzhe
    Fang, Jintao
    Wang, Tiexin
    Li, Bohan
    WEB INFORMATION SYSTEMS AND APPLICATIONS, WISA 2024, 2024, 14883 : 331 - 363
  • [5] The Importance of Understanding Language in Large Language Models
    Youssef, Alaa
    Stein, Samantha
    Clapp, Justin
    Magnus, David
    AMERICAN JOURNAL OF BIOETHICS, 2023, 23 (10): : 6 - 7
  • [6] Large Language Models are Not Models of Natural Language: They are Corpus Models
    Veres, Csaba
    IEEE ACCESS, 2022, 10 : 61970 - 61979
  • [7] HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language Models
    Ren, Yuqi
    Xiong, Deyi
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023), 2023, : 12350 - 12365
  • [8] Understanding Telecom Language Through Large Language Models
    Bariah, Lina
    Zou, Hang
    Zhao, Qiyang
    Mouhouche, Belkacem
    Bader, Faouzi
    Debbah, Merouane
    IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 6542 - 6547
  • [9] Combining large language models with enterprise knowledge graphs: a perspective on enhanced natural language understanding
    Mariotti, Luca
    Guidetti, Veronica
    Mandreoli, Federica
    Belli, Andrea
    Lombardi, Paolo
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2024, 7
  • [10] Natural language processing in the era of large language models
    Zubiaga, Arkaitz
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2024, 6
12345