14 citations · 50 across the 12 of their papers we have counts for
12 papers
Exploring Text Classification Models with Sparse Autoencoders
Daniel Kerrigan, Brian Barr, Enrico Bertini
As language models (LMs) rise in prominence, there is interest in making them more transparent in order to better understand their internal behavior. Recent interpretability work h…
MOUNTAINEER: Topology-Driven Visual Analytics for Comparing Local Explanations
Parikshit Solunke, Vitoria Guardieiro, Joao Rulff +5
With the increasing use of black-box Machine Learning (ML) techniques in critical applications, there is a growing demand for methods that can provide transparency and accountabili…
T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients
Evandro S. Ortigossa, Fábio F. Dias, Brian Barr +2
The development of machine learning applications has increased significantly in recent years, motivated by the remarkable ability of learning-powered systems to discover and genera…
The Disagreement Problem in Faithfulness Metrics
Brian Barr, Noah Fatsi, Leif Hancox-Li +3
The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work. Much of the work centers around the holy grail of providing post-…
BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence
Isha Hameed, Samuel Sharpe, Daniel Barcklow +5
Explainable artificial intelligence (XAI) methods lack ground truth. In its place, method developers have relied on axioms to determine desirable properties for their explanations'…
Calibrate: Interactive Analysis of Probabilistic Model Output
Peter Xenopoulos, Joao Rulff, Luis Gustavo Nonato +2
Analyzing classification model performance is a crucial task for machine learning practitioners. While practitioners often use count-based metrics derived from confusion matrices,…