Anna Hedström

25 papers A* 5Journal 17Unranked 3
YearRankTypeTitle / Venue / Authors
2026 A* conf
Benchmarking XAI Explanations with Human-Aligned Evaluations.
AAAI
Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier, Anna Hedström, Patricia Delhomme, David Filliat, Nicolas Bousquet, Goran Frehse, Massimiliano Mancini, Baptiste Caramiaux, Andrea Passerini, Gianni Franchi
2025 J jnl
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework.
CoRR
Laura Kopf, Nils Feldhus, Kirill Bykov, Philine Lou Bommer, Anna Hedström, Marina M.-C. Höhne, Oliver Eberle
2025 A* conf
Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution.
AAAI
Carlos Eiras-Franco, Anna Hedström, Marina M.-C. Höhne
2025 J jnl
Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution.
CoRR
Carlos Eiras-Franco, Anna Hedström, Marina M.-C. Höhne
2025 J jnl
Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions.
Trans. Mach. Learn. Res.
Anna Hedström, Philine Lou Bommer, Thomas F. Burns, Sebastian Lapuschkin, Wojciech Samek, Marina M.-C. Höhne
2025 A* conf
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models.
ICML
Anna Hedström, Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Manuela Veloso
2025 J jnl
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models.
CoRR
Anna Hedström, Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Manuela Veloso
2024 — conf
A Fresh Look at Sanity Checks for Saliency Maps.
xAI (1)
Anna Hedström, Leander Weber, Sebastian Lapuschkin, Marina M.-C. Höhne
2024 J jnl
A Fresh Look at Sanity Checks for Saliency Maps.
CoRR
Anna Hedström, Leander Weber, Sebastian Lapuschkin, Marina M.-C. Höhne
2024 J jnl
Benchmarking XAI Explanations with Human-Aligned Evaluations.
CoRR
Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier, Anna Hedström, Patricia Delhomme, Nicolas Bousquet, Goran Frehse, Massimiliano Mancini, Baptiste Caramiaux, Andrea Passerini, Gianni Franchi
2024 A* conf
CoSy: Evaluating Textual Explanations of Neurons.
NeurIPS
Laura Kopf, Philine Lou Bommer, Anna Hedström, Sebastian Lapuschkin, Marina M.-C. Höhne, Kirill Bykov
2024 J jnl
CoSy: Evaluating Textual Explanations of Neurons.
CoRR
Laura Kopf, Philine Lou Bommer, Anna Hedström, Sebastian Lapuschkin, Marina M.-C. Höhne, Kirill Bykov
2024 — conf
Explainable AI in grassland monitoring: Enhancing model performance and domain adaptability.
GIL
Shanghua Liu, Anna Hedström, Deepak Hanike Basavegowda, Cornelia Weltzien, Marina M.-C. Höhne
2024 — conf
From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation.
ECCV Workshops (21)
Kristoffer Wickstrøm, Marina M.-C. Höhne, Anna Hedström
2024 J jnl
From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation.
CoRR
Kristoffer Wickstrøm, Marina Marie-Claire Höhne, Anna Hedström
2024 J jnl
Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond.
CoRR
Dilyara Bareeva, Galip Ümit Yolcu, Anna Hedström, Niklas Schmolenski, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2024 J jnl
Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test.
CoRR
Anna Hedström, Leander Weber, Sebastian Lapuschkin, Marina M.-C. Höhne
2023 J jnl
Explainable AI in Grassland Monitoring: Enhancing Model Performance and Domain Adaptability.
CoRR
Shanghua Liu, Anna Hedström, Deepak Hanike Basavegowda, Cornelia Weltzien, Marina M.-C. Höhne
2023 J jnl
Finding the right XAI method - A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science.
CoRR
Philine Lou Bommer, Marlene Kretschmer, Anna Hedström, Dilyara Bareeva, Marina M.-C. Höhne
2023 J jnl
Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond.
J. Mach. Learn. Res.
Anna Hedström, Leander Weber, Daniel Krakowczyk, Dilyara Bareeva, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2023 J jnl
The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus.
CoRR
Anna Hedström, Philine Lou Bommer, Kristoffer K. Wickstrøm, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2023 J jnl
The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus.
Trans. Mach. Learn. Res.
Anna Hedström, Philine Lou Bommer, Kristoffer Knutsen Wickstrøm, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2022 A* conf
NoiseGrad - Enhancing Explanations by Introducing Stochasticity to Model Weights.
AAAI
Kirill Bykov, Anna Hedström, Shinichi Nakajima, Marina M.-C. Höhne
2022 J jnl
Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations.
CoRR
Anna Hedström, Leander Weber, Dilyara Bareeva, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2021 J jnl
NoiseGrad: enhancing explanations by introducing stochasticity to model weights.
CoRR
Kirill Bykov, Anna Hedström, Shinichi Nakajima, Marina M.-C. Höhne