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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations


Nov 14, 2022
Swarnadeep Saha, Peter Hase, Nazneen Rajani, Mohit Bansal

* EMNLP 2022 (11 pages) 

   Access Paper or Ask Questions

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

Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees


Sep 21, 2022
Swarnadeep Saha, Shiyue Zhang, Peter Hase, Mohit Bansal

* 24 pages (10 figures, 7 tables) 

   Access Paper or Ask Questions

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

VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives


Jun 22, 2022
Zhuofan Ying, Peter Hase, Mohit Bansal

* 24 pages, 10 figures (First two authors contributed equally) 

   Access Paper or Ask Questions

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

GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models


Mar 14, 2022
Archiki Prasad, Peter Hase, Xiang Zhou, Mohit Bansal


   Access Paper or Ask Questions

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

Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs


Nov 26, 2021
Peter Hase, Mona Diab, Asli Celikyilmaz, Xian Li, Zornitsa Kozareva, Veselin Stoyanov, Mohit Bansal, Srinivasan Iyer

* 19 pages 

   Access Paper or Ask Questions

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

Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions


Nov 01, 2021
Prateek Yadav, Peter Hase, Mohit Bansal

* 26 pages, 6 figures, 8 tables, 5 algorithms 

   Access Paper or Ask Questions

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

Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals


Jun 01, 2021
Peter Hase, Harry Xie, Mohit Bansal

* 26 pages, 4 figures, 8 tables 

   Access Paper or Ask Questions

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

When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data


Feb 10, 2021
Peter Hase, Mohit Bansal

* 25 pages, 20 figures 

   Access Paper or Ask Questions

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

FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging


Dec 31, 2020
Han Guo, Nazneen Fatema Rajani, Peter Hase, Mohit Bansal, Caiming Xiong

* 18 pages 

   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
>>