Benedict Clark

12 papers A* 1Journal 11
YearRankTypeTitle / Venue / Authors
2026 J jnl
Feature salience - not task-informativeness - drives machine learning model explanations.
CoRR
Benedict Clark, Marta Oliveira, Rick Wilming, Stefan Haufe
2026 J jnl
The effect of whitening on explanation performance.
CoRR
Benedict Clark, Stoyan Karastoyanov, Rick Wilming, Stefan Haufe
2025 J jnl
GECOBench: a gender-controlled text dataset and benchmark for quantifying biases in explanations.
Frontiers Artif. Intell.
Rick Wilming, Artur Dox, Hjalmar Schulz, Marta Oliveira, Benedict Clark, Stefan Haufe
2024 J jnl
Benchmarking the influence of pre-training on explanation performance in MR image classification.
Frontiers Artif. Intell.
Marta Oliveira, Rick Wilming, Benedict Clark, Céline Budding, Fabian Eitel, Kerstin Ritter, Stefan Haufe
2024 J jnl
EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods.
CoRR
Benedict Clark, Rick Wilming, Artur Dox, Paul Eschenbach, Sami Hached, Daniel Jin Wodke, Michias Taye Zewdie, Uladzislau Bruila, Marta Oliveira, Hjalmar Schulz, Luca Matteo Cornils, Danny Panknin, Ahcène Boubekki, Stefan Haufe
2024 J jnl
Explainable AI needs formal notions of explanation correctness.
CoRR
Stefan Haufe, Rick Wilming, Benedict Clark, Rustam Zhumagambetov, Danny Panknin, Ahcène Boubekki
2024 J jnl
GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations.
CoRR
Rick Wilming, Artur Dox, Hjalmar Schulz, Marta Oliveira, Benedict Clark, Stefan Haufe
2024 J jnl
XAI-TRIS: non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance.
Mach. Learn.
Benedict Clark, Rick Wilming, Stefan Haufe
2023 J jnl
Benchmark data to study the influence of pre-training on explanation performance in MR image classification.
CoRR
Marta Oliveira, Rick Wilming, Benedict Clark, Céline Budding, Fabian Eitel, Kerstin Ritter, Stefan Haufe
2023 A* conf
Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables.
ICML
Rick Wilming, Leo Kieslich, Benedict Clark, Stefan Haufe
2023 J jnl
Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables.
CoRR
Rick Wilming, Leo Kieslich, Benedict Clark, Stefan Haufe
2023 J jnl
XAI-TRIS: Non-linear benchmarks to quantify ML explanation performance.
CoRR
Benedict Clark, Rick Wilming, Stefan Haufe