Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Selective Annotation Makes Language Models Better Few-Shot Learners


Sep 05, 2022
Hongjin Su, Jungo Kasai, Chen Henry Wu, Weijia Shi, Tianlu Wang, Jiayi Xin, Rui Zhang, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale


Aug 15, 2022
Tim Dettmers, Mike Lewis, Younes Belkada, Luke Zettlemoyer

* Extended NeurIPS2022 submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models


Aug 05, 2022
Margaret Li, Suchin Gururangan, Tim Dettmers, Mike Lewis, Tim Althoff, Noah A. Smith, Luke Zettlemoyer


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Questions Are All You Need to Train a Dense Passage Retriever


Jun 21, 2022
Devendra Singh Sachan, Mike Lewis, Dani Yogatama, Luke Zettlemoyer, Joelle Pineau, Manzil Zaheer


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

LegoNN: Building Modular Encoder-Decoder Models


Jun 07, 2022
Siddharth Dalmia, Dmytro Okhonko, Mike Lewis, Sergey Edunov, Shinji Watanabe, Florian Metze, Luke Zettlemoyer, Abdelrahman Mohamed

* 13 pages; Submitted to TASLP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Nearest Neighbor Zero-Shot Inference


May 27, 2022
Weijia Shi, Julian Michael, Suchin Gururangan, Luke Zettlemoyer


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI


May 25, 2022
Suzanna Sia, Anton Belyy, Amjad Almahairi, Madian Khabsa, Luke Zettlemoyer, Lambert Mathias

* Under Review 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models


May 24, 2022
Terra Blevins, Hila Gonen, Luke Zettlemoyer


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Role of Bidirectionality in Language Model Pre-Training


May 24, 2022
Mikel Artetxe, Jingfei Du, Naman Goyal, Luke Zettlemoyer, Ves Stoyanov


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models


May 22, 2022
Kushal Tirumala, Aram H. Markosyan, Luke Zettlemoyer, Armen Aghajanyan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
7
>>