Salman Rahman

I am a Computer Science graduate student at New York University. My research goal is to improve the trustworthiness of artificial intelligence systems by ensuring AI systems smarter than humans align with human interests and evaluating and mitigating the catastrophic risks posed by AI systems. My research takes shape in two key directions:

adjust
Scalable Oversight
Supervising capable but unreliable experts on complex tasks using multiagent debate.
adjust
Model Evaluation for Extreme Risks
Evaluation and mitigation of risks posed by large models.

Earlier in my academic journey, I delved into computational sustainability during my undergrad and master's studies. I was captivated by the prospect of leveraging technology to provide solutions to the pressing societal and environmental challenges of the 21st century. Explore my publications on computational sustainability here.

News

Mar 30, 2024

One paper on machine learning explanation disparity is accepted to ACM FAccT 2024.

Selected Publications

Image description

Understanding Disparities in Post Hoc Machine Learning Explanation

Vishwali Mhasawade, Salman Rahman, Zoe Haskell-Craig, Rumi Chunara

FAccT, 2024 PDF

Healthcare AI Model

Generalization in Healthcare AI: Evaluation of a Clinical Large Language Model

Salman Rahman, Lavender Yao Jiang, Saadia Gabriel, Yindalon Aphinyanaphongs, Eric Karl Oermann, Rumi Chunara

arXiv preprint, 2024 PDF

Healthcare AI Model

Impact on Public Health Decision Making by Utilizing Big Data Without Domain Knowledge

Miao Zhang, Salman Rahman, Vishwali Mhasawade, Rumi Chunara

arXiv preprint, 2024 PDF

Landslide Susceptibility Mapping

Improving Spatial Agreement in Machine Learning-based Landslide Susceptibility Mapping

Mohammed Sarfaraz Gani Adnan, Salman Rahman, Nahian Ahmed, Bayes Ahmed, Md. Fazleh Rabbi, Rashedur M. Rahman

Remote Sensing, 2020 HTML

Teaching

Fall 2023

Guest Lecturer, Foundation(Large) Language Model
CS-GY 9223: Foundations of Data Science, Graduate, NYU