Picture for Chirag Nagpal

Chirag Nagpal

A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models

Add code
Mar 18, 2024
Stephen R. Pfohl, Heather Cole-Lewis, Rory Sayres, Darlene Neal, Mercy Asiedu, Awa Dieng, Nenad Tomasev, Qazi Mamunur Rashid, Shekoofeh Azizi, Negar Rostamzadeh, Liam G. McCoy, Leo Anthony Celi, Yun Liu, Mike Schaekermann, Alanna Walton, Alicia Parrish, Chirag Nagpal, Preeti Singh, Akeiylah Dewitt, Philip Mansfield, Sushant Prakash, Katherine Heller, Alan Karthikesalingam, Christopher Semturs, Joelle Barral, Greg Corrado, Yossi Matias, Jamila Smith-Loud, Ivor Horn, Karan Singhal

Figure 1 for A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Figure 2 for A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Figure 3 for A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Figure 4 for A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Viaarxiv icon

The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa

Add code
Mar 11, 2024
Mercy Asiedu, Awa Dieng, Iskandar Haykel, Negar Rostamzadeh, Stephen Pfohl, Chirag Nagpal, Maria Nagawa, Abigail Oppong, Sanmi Koyejo, Katherine Heller

Figure 1 for The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa
Figure 2 for The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa
Figure 3 for The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa
Figure 4 for The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa
Viaarxiv icon

Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation

Add code
Feb 20, 2024
Kristian Lum, Jacy Reese Anthis, Chirag Nagpal, Alexander D'Amour

Figure 1 for Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation
Viaarxiv icon

Transforming and Combining Rewards for Aligning Large Language Models

Add code
Feb 01, 2024
Zihao Wang, Chirag Nagpal, Jonathan Berant, Jacob Eisenstein, Alex D'Amour, Sanmi Koyejo, Victor Veitch

Viaarxiv icon

Theoretical guarantees on the best-of-n alignment policy

Add code
Jan 03, 2024
Ahmad Beirami, Alekh Agarwal, Jonathan Berant, Alexander D'Amour, Jacob Eisenstein, Chirag Nagpal, Ananda Theertha Suresh

Viaarxiv icon

Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Add code
Dec 21, 2023
Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D'Amour, DJ Dvijotham, Adam Fisch, Katherine Heller, Stephen Pfohl, Deepak Ramachandran, Peter Shaw, Jonathan Berant

Viaarxiv icon

Recovering Sparse and Interpretable Subgroups with Heterogeneous Treatment Effects with Censored Time-to-Event Outcomes

Add code
Feb 24, 2023
Chirag Nagpal, Vedant Sanil, Artur Dubrawski

Figure 1 for Recovering Sparse and Interpretable Subgroups with Heterogeneous Treatment Effects with Censored Time-to-Event Outcomes
Figure 2 for Recovering Sparse and Interpretable Subgroups with Heterogeneous Treatment Effects with Censored Time-to-Event Outcomes
Figure 3 for Recovering Sparse and Interpretable Subgroups with Heterogeneous Treatment Effects with Censored Time-to-Event Outcomes
Figure 4 for Recovering Sparse and Interpretable Subgroups with Heterogeneous Treatment Effects with Censored Time-to-Event Outcomes
Viaarxiv icon

Participatory Systems for Personalized Prediction

Add code
Feb 08, 2023
Hailey James, Chirag Nagpal, Katherine Heller, Berk Ustun

Figure 1 for Participatory Systems for Personalized Prediction
Figure 2 for Participatory Systems for Personalized Prediction
Figure 3 for Participatory Systems for Personalized Prediction
Figure 4 for Participatory Systems for Personalized Prediction
Viaarxiv icon

auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data

Add code
Apr 15, 2022
Chirag Nagpal, Willa Potosnak, Artur Dubrawski

Figure 1 for auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data
Figure 2 for auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data
Figure 3 for auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data
Figure 4 for auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data
Viaarxiv icon

Counterfactual Phenotyping with Censored Time-to-Events

Add code
Feb 22, 2022
Chirag Nagpal, Mononito Goswami, Keith Dufendach, Artur Dubrawski

Figure 1 for Counterfactual Phenotyping with Censored Time-to-Events
Figure 2 for Counterfactual Phenotyping with Censored Time-to-Events
Figure 3 for Counterfactual Phenotyping with Censored Time-to-Events
Figure 4 for Counterfactual Phenotyping with Censored Time-to-Events
Viaarxiv icon