Search Results for author:
Found 3 papers, 0 papers with code
Echoes of Biases: How Stigmatizing Language Affects AI Performance
To explore an operationally efficient way to mitigate SL's impact, we investigate patterns in the generation of SL through a clinicians' collaborative network, identifying central clinicians as having a stronger impact on racial disparity in the AI model.
Explainable Artificial Intelligence (XAI)
Mortality Prediction
Catch Me If You Can: Identifying Fraudulent Physician Reviews with Large Language Models Using Generative Pre-Trained Transformers
Our findings reveal significantly superior performance of GPT-3 over traditional ML models in this context.
Finding patterns in Knowledge Attribution for Transformers
We analyze the Knowledge Neurons framework for the attribution of factual and relational knowledge to particular neurons in the transformer network.
