Search Results - "Sayenju, Sudhashree"

Quantifying Domain Knowledge in Large Language Models by Sayenju, Sudhashree, Aygun, Ramazan, Franks, Bill, Johnston, Sereres, Lee, George, Choi, Hansook, Modgil, Girish

“…Transformer based Large language models such as BERT, have demonstrated the ability to derive contextual information from the words surrounding it. However,…”
Get full text

Stereotype and Categorical Bias Evaluation via Differential Cosine Bias Measure by Sayenju, Sudhashree, Aygun, Ramazan, Franks, Bill, Johnston, Sereres, Lee, George, Modgil, Girish

“…A vast range of Natural Language Processing (NLP) systems that are in use today have direct impact on humans. While machine learning models are expected to…”
Get full text

Explainability Audit: An Automated Evaluation of Local Explainability in Rooftop Image Classification by Don, Duleep Rathamage, Boardman, Jonathan, Sayenju, Sudhashree, Aygun, Ramazan, Zhang, Yifan, Franks, Bill, Johnston, Sereres, Lee, George, Sullivan, Dan, Modgil, Girish

“…Explainable Artificial Intelligence (XAI) is a key concept in building trustworthy machine learning models. Local explainability methods seek to provide…”
Get full text

Directional Pairwise Class Confusion Bias and Its Mitigation by Sayenju, Sudhashree, Aygun, Ramazan, Boardman, Jonathan, Don, Duleep Prasanna Rathgamage, Zhang, Yifan, Franks, Bill, Johnston, Sereres, Lee, George, Sullivan, Dan, Modgil, Girish

“…Recent advances in Natural Language Processing have led to powerful and sophisticated models like BERT (Bidirectional Encoder Representations from…”
Get full text