Oliver Eberle

32 papers A* 4B 1Journal 21Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology.
CoRR
Mina Jamshidi Idaji, Julius Hense, Tom Neuhäuser, Augustin Krause, Yanqing Luo, Oliver Eberle, Thomas Schnake, Laure Ciernik, Farnoush Rezaei Jafari, Reza Vahidimajd, Jonas Dippel, Christoph Walz, Frederick Klauschen, Andreas Mock, Klaus-Robert Müller
2025 J jnl
Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models.
CoRR
Samuel Lippl, Thomas McGee, Kimberly Lopez, Ziwen Pan, Pierce Zhang, Salma Ziadi, Oliver Eberle, Ida Momennejad
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 J jnl
Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments.
CoRR
Lorenz Linhardt, Tom Neuhäuser, Lenka Tetková, Oliver Eberle
2025 B conf
How do LLMs Solve Multi-step Reasoning? An Algorithmic Evaluation.
CogSci
Oliver Eberle, Thomas McGee, Hamza Giaffar, Taylor W. Webb, Ida Momennejad
2025 — conf
Position: We Need An Algorithmic Understanding of Generative AI.
ICML (Position Papers)
Oliver Eberle, Thomas McGee, Hamza Giaffar, Taylor Whittington Webb, Ida Momennejad
2025 J jnl
Position: We Need An Algorithmic Understanding of Generative AI.
CoRR
Oliver Eberle, Thomas McGee, Hamza Giaffar, Taylor W. Webb, Ida Momennejad
2025 J jnl
RelP: Faithful and Efficient Circuit Discovery via Relevance Patching.
CoRR
Farnoush Rezaei Jafari, Oliver Eberle, Ashkan Khakzar, Neel Nanda
2025 — conf
Trick or Neat: Adversarial Ambiguity and Language Model Evaluation.
ACL (Findings)
Antonia Karamolegkou, Oliver Eberle, Phillip Rust, Carina Kauf, Anders Søgaard
2025 J jnl
Trick or Neat: Adversarial Ambiguity and Language Model Evaluation.
CoRR
Antonia Karamolegkou, Oliver Eberle, Phillip Rust, Carina Kauf, Anders Søgaard
2024 J jnl
Comparing zero-shot self-explanations with human rationales in multilingual text classification.
CoRR
Stephanie Brandl, Oliver Eberle
2024 — conf
Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations.
LREC/COLING
Stephanie Brandl, Oliver Eberle, Tiago Ribeiro, Anders Søgaard, Nora Hollenstein
2024 J jnl
Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations.
CoRR
Stephanie Brandl, Oliver Eberle, Tiago Ribeiro, Anders Søgaard, Nora Hollenstein
2024 — conf
Explaining Text Similarity in Transformer Models.
NAACL-HLT
Alexandros Vasileiou, Oliver Eberle
2024 J jnl
Explaining Text Similarity in Transformer Models.
CoRR
Alexandros Vasileiou, Oliver Eberle
2024 A* conf
MambaLRP: Explaining Selective State Space Sequence Models.
NeurIPS
Farnoush Rezaei Jafari, Grégoire Montavon, Klaus-Robert Müller, Oliver Eberle
2024 J jnl
MambaLRP: Explaining Selective State Space Sequence Models.
CoRR
Farnoush Rezaei Jafari, Grégoire Montavon, Klaus-Robert Müller, Oliver Eberle
2024 A* conf
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology.
NeurIPS
Julius Hense, Mina Jamshidi Idaji, Oliver Eberle, Thomas Schnake, Jonas Dippel, Laure Ciernik, Oliver Buchstab, Andreas Mock, Frederick Klauschen, Klaus-Robert Müller
2024 J jnl
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology.
CoRR
Julius Hense, Mina Jamshidi Idaji, Oliver Eberle, Thomas Schnake, Jonas Dippel, Laure Ciernik, Oliver Buchstab, Andreas Mock, Frederick Klauschen, Klaus-Robert Müller
2023 J jnl
Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI.
CoRR
Oliver Eberle, Jochen Büttner, Hassan El-Hajj, Grégoire Montavon, Klaus-Robert Müller, Matteo Valleriani
2023 A* conf
Rather a Nurse than a Physician - Contrastive Explanations under Investigation.
EMNLP
Oliver Eberle, Ilias Chalkidis, Laura Cabello, Stephanie Brandl
2023 J jnl
Rather a Nurse than a Physician - Contrastive Explanations under Investigation.
CoRR
Oliver Eberle, Ilias Chalkidis, Laura Cabello, Stephanie Brandl
2022 J jnl
An Ever-Expanding Humanities Knowledge Graph: The Sphaera Corpus at the Intersection of Humanities, Data Management, and Machine Learning.
Datenbank-Spektrum
Hassan El-Hajj, Maryam Zamani, Jochen Büttner, Julius Martinetz, Oliver Eberle, Noga Shlomi, Anna Siebold, Grégoire Montavon, Klaus-Robert Müller, Holger Kantz, Matteo Valleriani
2022 J jnl
Building and Interpreting Deep Similarity Models.
IEEE Trans. Pattern Anal. Mach. Intell.
Oliver Eberle, Jochen Büttner, Florian Kräutli, Klaus-Robert Müller, Matteo Valleriani, Grégoire Montavon
2022 — conf
Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?
ACL (1)
Oliver Eberle, Stephanie Brandl, Jonas Pilot, Anders Søgaard
2022 J jnl
Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?
CoRR
Stephanie Brandl, Oliver Eberle, Jonas Pilot, Anders Søgaard
2022 — —
Explainable structured machine learning: insights into similarity, graph and transformer models.
Oliver Eberle
2022 J jnl
Higher-Order Explanations of Graph Neural Networks via Relevant Walks.
IEEE Trans. Pattern Anal. Mach. Intell.
Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Grégoire Montavon
2022 A* conf
XAI for Transformers: Better Explanations through Conservative Propagation.
ICML
Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf
2022 J jnl
XAI for Transformers: Better Explanations through Conservative Propagation.
CoRR
Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf
2020 J jnl
Building and Interpreting Deep Similarity Models.
CoRR
Oliver Eberle, Jochen Büttner, Florian Kräutli, Klaus-Robert Müller, Matteo Valleriani, Grégoire Montavon
2020 J jnl
XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks.
CoRR
Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Grégoire Montavon