Search Results for author: Stephen Pfohl

Found 9 papers, 0 papers with code

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

no code implementations5 Mar 2024 Mercy Asiedu, Awa Dieng, Iskandar Haykel, Negar Rostamzadeh, Stephen Pfohl, Chirag Nagpal, Maria Nagawa, Abigail Oppong, Sanmi Koyejo, Katherine Heller

Whereas experts generally expressed a shared view about the relevance of colonial history for the development and implementation of AI technologies in Africa, the majority of the general population participants surveyed did not think there was a direct link between AI and colonialism.

Attribute Fairness

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

no code implementations14 Dec 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

However, even pretrain reward ensembles do not eliminate reward hacking: we show several qualitative reward hacking phenomena that are not mitigated by ensembling because all reward models in the ensemble exhibit similar error patterns.

Language Modelling

Counterfactual Reasoning for Fair Clinical Risk Prediction

no code implementations14 Jul 2019 Stephen Pfohl, Tony Duan, Daisy Yi Ding, Nigam H. Shah

We investigate the extent to which the augmented counterfactual fairness criteria may be applied to develop fair models for prolonged inpatient length of stay and mortality with observational electronic health records data.

Attribute counterfactual +4

Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk

no code implementations12 Sep 2018 Stephen Pfohl, Ben Marafino, Adrien Coulet, Fatima Rodriguez, Latha Palaniappan, Nigam H. Shah

Guidelines for the management of atherosclerotic cardiovascular disease (ASCVD) recommend the use of risk stratification models to identify patients most likely to benefit from cholesterol-lowering and other therapies.

Fairness Management

The Effectiveness of Multitask Learning for Phenotyping with Electronic Health Records Data

no code implementations9 Aug 2018 Daisy Yi Ding, Chloé Simpson, Stephen Pfohl, Dave C. Kale, Kenneth Jung, Nigam H. Shah

We present experiments that elucidate when multitask learning with neural nets improves performance for phenotyping using EHR data relative to neural nets trained for a single phenotype and to well-tuned logistic regression baselines.

Cannot find the paper you are looking for? You can Submit a new open access paper.