A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts

G Schwalbe, B Finzel - Data Mining and Knowledge Discovery, 2024 - Springer
In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation
criteria have been developed within the research field of explainable artificial intelligence …

Adversarial attacks and defenses in explainable artificial intelligence: A survey

H Baniecki, P Biecek - Information Fusion, 2024 - Elsevier
Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging
and trusting statistical and deep learning models, as well as interpreting their predictions …

Dalex: responsible machine learning with interactive explainability and fairness in python

H Baniecki, W Kretowicz, P PiÄ, J WiĹ - Journal of Machine Learning …, 2021 - jmlr.org
In modern machine learning, we observe the phenomenon of opaqueness debt, which
manifests itself by an increased risk of discrimination, lack of reproducibility, and deated …

Explainable and interpretable machine learning and data mining

M Atzmueller, J Fürnkranz, T Kliegr… - Data Mining and …, 2024 - Springer
The growing number of applications of machine learning and data mining in many domains—
from agriculture to business, education, industrial manufacturing, and medicine—gave rise …

survex: an R package for explaining machine learning survival models

M Spytek, M Krzyziński, SH Langbein, H Baniecki… - …, 2023 - academic.oup.com
Due to their flexibility and superior performance, machine learning models frequently
complement and outperform traditional statistical survival models. However, their …

shapiq: Shapley interactions for machine learning

M Muschalik, H Baniecki, F Fumagalli… - arXiv preprint arXiv …, 2024 - arxiv.org
Originally rooted in game theory, the Shapley Value (SV) has recently become an important
tool in machine learning research. Perhaps most notably, it is used for feature attribution and …

Explanation as a process: user-centric construction of multi-level and multi-modal explanations

B Finzel, DE Tafler, S Scheele, U Schmid - KI 2021: Advances in Artificial …, 2021 - Springer
In the last years, XAI research has mainly been concerned with developing new technical
approaches to explain deep learning models. Just recent research has started to …

Exploration of Rashomon set assists explanations for medical data

K Kobylińska, M Krzyziński, R Machowicz… - arXiv preprint arXiv …, 2023 - arxiv.org
The machine learning modeling process conventionally culminates in selecting a single
model that maximizes a selected performance metric. However, this approach leads to …

Explainable artificial intelligence based fault diagnosis and insight harvesting for steel plates manufacturing

A Kharal - arXiv preprint arXiv:2008.04448, 2020 - arxiv.org
With the advent of Industry 4.0, Data Science and Explainable Artificial Intelligence (XAI) has
received considerable intrest in recent literature. However, the entry threshold into XAI, in …

Explain to Question not to Justify

P Biecek, W Samek - arXiv preprint arXiv:2402.13914, 2024 - arxiv.org
Explainable Artificial Intelligence (XAI) is a young but very promising field of research.
Unfortunately, the progress in this field is currently slowed down by divergent and …