Search Results for author:
Found 11 papers, 9 papers with code
From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation
The lack of ground truth explanation labels is a fundamental challenge for quantitative evaluation in explainable artificial intelligence (XAI).
Benchmarking XAI Explanations with Human-Aligned Evaluations
Our first key contribution is a human evaluation of XAI explanations on four diverse datasets (COCO, Pascal Parts, Cats Dogs Cars, and MonumAI) which constitutes the first large-scale benchmark dataset for XAI, with annotations at both the image and concept levels.
Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond
In recent years, training data attribution (TDA) methods have emerged as a promising direction for the interpretability of neural networks.
CoSy: Evaluating Textual Explanations of Neurons
A crucial aspect of understanding the complex nature of Deep Neural Networks (DNNs) is the ability to explain learned concepts within their latent representations.
A Fresh Look at Sanity Checks for Saliency Maps
The Model Parameter Randomisation Test (MPRT) is highly recognised in the eXplainable Artificial Intelligence (XAI) community due to its fundamental evaluative criterion: explanations should be sensitive to the parameters of the model they seek to explain.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test
The Model Parameter Randomisation Test (MPRT) is widely acknowledged in the eXplainable Artificial Intelligence (XAI) community for its well-motivated evaluative principle: that the explanation function should be sensitive to changes in the parameters of the model function.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Explainable AI in Grassland Monitoring: Enhancing Model Performance and Domain Adaptability
Grasslands are known for their high biodiversity and ability to provide multiple ecosystem services.
Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science
We find architecture-dependent performance differences regarding robustness, complexity and localization skills of different XAI methods, highlighting the necessity for research task-specific evaluation.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus
We address this problem through a meta-evaluation of different quality estimators in XAI, which we define as ''the process of evaluating the evaluation method''.
Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness.
NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights
For local explanation, stochasticity is known to help: a simple method, called SmoothGrad, has improved the visual quality of gradient-based attribution by adding noise to the input space and averaging the explanations of the noisy inputs.
