9 papers
Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models
Patrick Knab, Sascha Marton, Christian Bartelt
LIME (Local Interpretable Model-agnostic Explanations) is a popular XAI framework for unraveling decision-making processes in vision machine-learning models. The technique utilizes…
Disentangling Exploration of Large Language Models by Optimal Exploitation
Tim Grams, Patrick Betz, Sascha Marton +2
Exploration is a crucial skill for in-context reinforcement learning in unknown environments. However, it remains unclear if large language models can effectively explore a partial…
DCBM: Data-Efficient Visual Concept Bottleneck Models
Katharina Prasse, Patrick Knab, Sascha Marton +2
Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on con…
Which LIME should I trust? Concepts, Challenges, and Solutions
Patrick Knab, Sascha Marton, Udo Schlegel +1
As neural networks become dominant in essential systems, Explainable Artificial Intelligence (XAI) plays a crucial role in fostering trust and detecting potential misbehavior of op…
Unreflected Use of Tabular Data Repositories Can Undermine Research Quality
Andrej Tschalzev, Lennart Purucker, Stefan Lüdtke +3
Data repositories have accumulated a large number of tabular datasets from various domains. Machine Learning researchers are actively using these datasets to evaluate novel approac…
Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization
Sascha Marton, Tim Grams, Florian Vogt +3
Reinforcement learning (RL) has seen significant success across various domains, but its adoption is often limited by the black-box nature of neural network policies, making them d…