5 papers
Sparse Autoencoder Features for Classifications and Transferability
Jack Gallifant, Shan Chen, Kuleen Sasse +3
Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transpa…
Controllable Hybrid Captioner for Improved Long-form Video Understanding
Kuleen Sasse, Efsun Sarioglu Kayi, Arun Reddy
Video data, especially long-form video, is extremely dense and high-dimensional. Text-based summaries of video content offer a way to represent query-relevant content in a much mor…
debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
Kuleen Sasse, Shan Chen, Jackson Pond +2
As Vision Language Models (VLMs) gain widespread use, their fairness remains under-explored. In this paper, we analyze demographic biases across five models and six datasets. We fi…
Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats
Kuleen Sasse, Carlos Aguirre, Isabel Cachola +2
WARNING: This paper contains content that maybe upsetting or offensive to some readers. Dog whistles are coded expressions with dual meanings: one intended for the general public (…
Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions
Kuleen Sasse, Shinjitha Vadlakonda, Richard E. Kennedy +1
Background: Machine learning methods for clinical named entity recognition and entity normalization systems can utilize both labeled corpora and Knowledge Graphs (KGs) for learning…