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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions


Jul 28, 2022
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Amir Feder, Abhilasha Ravichander, Marius Mosbach, Yonatan Belinkov, Hinrich Schütze, Yoav Goldberg


   Access Paper or Ask Questions

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

Analyzing Gender Representation in Multilingual Models


Apr 20, 2022
Hila Gonen, Shauli Ravfogel, Yoav Goldberg

* Published at RepL4NLP 2022 

   Access Paper or Ask Questions

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

Adversarial Concept Erasure in Kernel Space


Jan 28, 2022
Shauli Ravfogel, Francisco Vargas, Yoav Goldberg, Ryan Cotterell

* Preprint 

   Access Paper or Ask Questions

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

Linear Adversarial Concept Erasure


Jan 28, 2022
Shauli Ravfogel, Michael Twiton, Yoav Goldberg, Ryan Cotterell

* Preprint 

   Access Paper or Ask Questions

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

BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models


Jun 22, 2021
Elad Ben Zaken, Shauli Ravfogel, Yoav Goldberg


   Access Paper or Ask Questions

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

Neural Extractive Search


Jun 08, 2021
Shauli Ravfogel, Hillel Taub-Tabib, Yoav Goldberg

* Accepted as a demo paper in ACL2021 

   Access Paper or Ask Questions

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

Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction


May 19, 2021
Shauli Ravfogel, Grusha Prasad, Tal Linzen, Yoav Goldberg

* Equal contribution by SR and GP. Uploaded new version to fix typo in the abstract 

   Access Paper or Ask Questions

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

Contrastive Explanations for Model Interpretability


Mar 02, 2021
Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, Yoav Goldberg


   Access Paper or Ask Questions

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

Measuring and Improving Consistency in Pretrained Language Models


Feb 01, 2021
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, Yoav Goldberg


   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
>>