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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Towards Robust Off-Policy Evaluation via Human Inputs


Sep 18, 2022
Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez, Himabindu Lakkaraju

* 10 pages, 5 figures, 1 table. Appeared at AIES '22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society. Expanded version of arXiv:2103.15933 

   Access Paper or Ask Questions

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

Evaluating Explainability for Graph Neural Networks


Aug 19, 2022
Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik


   Access Paper or Ask Questions

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

TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues


Jul 08, 2022
Dylan Slack, Satyapriya Krishna, Himabindu Lakkaraju, Sameer Singh

* Pre-print; comments welcome! Reach out to [email protected] 

   Access Paper or Ask Questions

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

OpenXAI: Towards a Transparent Evaluation of Model Explanations


Jun 22, 2022
Chirag Agarwal, Eshika Saxena, Satyapriya Krishna, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju

* Preprint 

   Access Paper or Ask Questions

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

Flatten the Curve: Efficiently Training Low-Curvature Neural Networks


Jun 14, 2022
Suraj Srinivas, Kyle Matoba, Himabindu Lakkaraju, Francois Fleuret


   Access Paper or Ask Questions

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

A Human-Centric Take on Model Monitoring


Jun 06, 2022
Murtuza N Shergadwala, Himabindu Lakkaraju, Krishnaram Kenthapadi

* 4 pages, 0 figures 

   Access Paper or Ask Questions

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

Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post hoc Explanations


Jun 02, 2022
Tessa Han, Suraj Srinivas, Himabindu Lakkaraju


   Access Paper or Ask Questions

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

Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations


May 15, 2022
Jessica Dai, Sohini Upadhyay, Ulrich Aivodji, Stephen H. Bach, Himabindu Lakkaraju

* Accepted at AIES 2022 

   Access Paper or Ask Questions

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

Rethinking Stability for Attribution-based Explanations


Mar 14, 2022
Chirag Agarwal, Nari Johnson, Martin Pawelczyk, Satyapriya Krishna, Eshika Saxena, Marinka Zitnik, Himabindu Lakkaraju


   Access Paper or Ask Questions

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

Algorithmic Recourse in the Face of Noisy Human Responses


Mar 13, 2022
Martin Pawelczyk, Teresa Datta, Johannes van-den-Heuvel, Gjergji Kasneci, Himabindu Lakkaraju


   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
>>