Alert button
Picture for Satyapriya Krishna

Satyapriya Krishna

Alert button

Understanding the Effects of Iterative Prompting on Truthfulness

Feb 09, 2024
Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju

Viaarxiv icon

Black-Box Access is Insufficient for Rigorous AI Audits

Jan 25, 2024
Stephen Casper, Carson Ezell, Charlotte Siegmann, Noam Kolt, Taylor Lynn Curtis, Benjamin Bucknall, Andreas Haupt, Kevin Wei, Jérémy Scheurer, Marius Hobbhahn, Lee Sharkey, Satyapriya Krishna, Marvin Von Hagen, Silas Alberti, Alan Chan, Qinyi Sun, Michael Gerovitch, David Bau, Max Tegmark, David Krueger, Dylan Hadfield-Menell

Viaarxiv icon

On the Intersection of Self-Correction and Trust in Language Models

Nov 06, 2023
Satyapriya Krishna

Figure 1 for On the Intersection of Self-Correction and Trust in Language Models
Figure 2 for On the Intersection of Self-Correction and Trust in Language Models
Figure 3 for On the Intersection of Self-Correction and Trust in Language Models
Figure 4 for On the Intersection of Self-Correction and Trust in Language Models
Viaarxiv icon

Are Large Language Models Post Hoc Explainers?

Oct 10, 2023
Nicholas Kroeger, Dan Ley, Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju

Figure 1 for Are Large Language Models Post Hoc Explainers?
Figure 2 for Are Large Language Models Post Hoc Explainers?
Figure 3 for Are Large Language Models Post Hoc Explainers?
Figure 4 for Are Large Language Models Post Hoc Explainers?
Viaarxiv icon

On the Trade-offs between Adversarial Robustness and Actionable Explanations

Sep 28, 2023
Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju

Viaarxiv icon

Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten

Feb 10, 2023
Satyapriya Krishna, Jiaqi Ma, Himabindu Lakkaraju

Figure 1 for Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
Figure 2 for Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
Figure 3 for Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
Figure 4 for Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
Viaarxiv icon

TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues

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

Figure 1 for TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues
Figure 2 for TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues
Figure 3 for TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues
Figure 4 for TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues
Viaarxiv icon

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

Figure 1 for OpenXAI: Towards a Transparent Evaluation of Model Explanations
Figure 2 for OpenXAI: Towards a Transparent Evaluation of Model Explanations
Figure 3 for OpenXAI: Towards a Transparent Evaluation of Model Explanations
Figure 4 for OpenXAI: Towards a Transparent Evaluation of Model Explanations
Viaarxiv icon

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal

Mar 23, 2022
Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, Aram Galstyan

Figure 1 for Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Figure 2 for Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Figure 3 for Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Figure 4 for Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Viaarxiv icon