1 citations · 1 across the 5 of their papers we have counts for
7 papers
Inverted Detection and Control in Steering Vectors
Max Torop, Aria Masoomi, Jennifer Dy
Steering vectors (SVs) are widely used to influence the expression of concepts (e.g., truthfulness) in large language model outputs. A key assumption underpinning SVs is that they…
DISCO: Disentangled Communication Steering for Large Language Models
Max Torop, Aria Masoomi, Masih Eskandar +1
A variety of recent methods guide large language model outputs via the inference-time addition of steering vectors to residual-stream or attention-head representations. In contrast…
Grounding Multimodal Large Language Models with Quantitative Skin Attributes: A Retrieval Study
Max Torop, Masih Eskandar, Nicholas Kurtansky +6
Artificial Intelligence models have demonstrated significant success in diagnosing skin diseases, including cancer, showing the potential to assist clinicians in their analysis. Ho…
Axiomatic Explainer Globalness via Optimal Transport
Davin Hill, Josh Bone, Aria Masoomi +2
Explainability methods are often challenging to evaluate and compare. With a multitude of explainers available, practitioners must often compare and select explainers based on quan…
SmoothHess: ReLU Network Feature Interactions via Stein's Lemma
Max Torop, Aria Masoomi, Davin Hill +3
Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-…
Boundary-Aware Uncertainty for Feature Attribution Explainers
Davin Hill, Aria Masoomi, Max Torop +2
Post-hoc explanation methods have become a critical tool for understanding black-box classifiers in high-stakes applications. However, high-performing classifiers are often highly…
Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection
Max Torop, Sandesh Ghimire, Wenqian Liu +5
There are limited works showing the efficacy of unsupervised Out-of-Distribution (OOD) methods on complex medical data. Here, we present preliminary findings of our unsupervised OO…