Towards falsifiable interpretability research

22 October 2020

Papers citing "Towards falsifiable interpretability research"

50 / 52 papers shown

Title
STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports Tegan McCaslin Jide Alaga Samira Nedungadi Seth Donoughe Tom Reed Rishi Bommasani Chris Painter Luca Righetti 262 2 0 13 Aug 2025
Attribution Explanations for Deep Neural Networks: A Theoretical Perspective Huiqi Deng Hongbin Pei Quanshi Zhang Mengnan Du FAtt 160 1 0 11 Aug 2025
Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision LayerInternational Conference on Learning Representations (ICLR), 2025 Xinyue Hu Zhibin Duan Bo Chen Mingyuan Zhou UQCV BDL 344 2 0 28 May 2025
A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i Kola Ayonrinde Louis Jaburi MILM 486 3 0 01 May 2025
Compositionality Unlocks Deep Interpretable Models Thomas Dooms Ward Gauderis Geraint A. Wiggins José Oramas FAtt CoGe AI4CE 207 2 0 03 Apr 2025
Mind the Gap: Bridging the Divide Between AI Aspirations and the Reality of Autonomous Characterization Grace Guinan Addison Salvador Michelle A. Smeaton Andrew Glaws Hilary Egan Brian C. Wyatt Babak Anasori K. Fiedler M. Olszta Steven Spurgeon 315 5 0 25 Feb 2025
Benchmarking XAI Explanations with Human-Aligned Evaluations Rémi Kazmierczak Steve Azzolin Eloise Berthier Anna Hedström Patricia Delhomme ... Goran Frehse Baptiste Caramiaux Baptiste Caramiaux Andrea Passerini Gianni Franchi 428 5 0 04 Nov 2024
Confident Teacher, Confident Student? A Novel User Study Design for Investigating the Didactic Potential of Explanations and their Impact on Uncertainty Teodor Chiaburu Frank Haußer Felix Bießmann 174 0 0 10 Sep 2024
Auditing Local Explanations is Hard Robi Bhattacharjee U. V. Luxburg LRM MLAU FAtt 235 5 0 18 Jul 2024
This Probably Looks Exactly Like That: An Invertible Prototypical Network Zachariah Carmichael Timothy Redgrave Daniel Gonzalez Cedre Walter J. Scheirer BDL 313 5 0 16 Jul 2024
An Actionability Assessment Tool for Explainable AI Ronal Singh Tim Miller L. Sonenberg Eduardo Velloso F. Vetere Piers Howe Paul Dourish 121 2 0 19 Jun 2024
Mechanistic Interpretability for AI Safety -- A Review Leonard Bereska E. Gavves AI4CE 332 293 0 22 Apr 2024
Acoustic characterization of speech rhythm: going beyond metrics with recurrent neural networks Franccois Deloche Laurent Bonnasse-Gahot Judit Gervain 89 0 0 22 Jan 2024
Artificial Neural Nets and the Representation of Human Concepts Timo Freiesleben NAI 312 4 0 08 Dec 2023
On the Relationship Between Interpretability and Explainability in Machine Learning Benjamin Leblanc Pascal Germain FaML 398 1 0 20 Nov 2023
Training Dynamics of Contextual N-Grams in Language Models Lucia Quirke Lovis Heindrich Wes Gurnee Neel Nanda 234 6 0 01 Nov 2023
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research DirectionsInformation Fusion (Inf. Fusion), 2023 Luca Longo Mario Brcic Federico Cabitza Jaesik Choi Roberto Confalonieri ... Andrés Páez Wojciech Samek Johannes Schneider Timo Speith Simone Stumpf 474 357 0 30 Oct 2023
How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors? Zachariah Carmichael Walter J. Scheirer FAtt 246 8 0 27 Oct 2023
Identifying Interpretable Visual Features in Artificial and Biological Neural Systems David A. Klindt Sophia Sanborn Francisco Acosta Frédéric Poitevin Nina Miolane MILM FAtt 267 10 0 17 Oct 2023
NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations Yeong-Joon Ju Ji-Hoon Park Seong-Whan Lee AAML 205 0 0 11 Oct 2023
The Blame Problem in Evaluating Local Explanations, and How to Tackle it Amir Hossein Akhavan Rahnama ELM FAtt 241 7 0 05 Oct 2023
Pixel-Grounded Prototypical Part NetworksIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 Zachariah Carmichael Suhas Lohit A. Cherian Michael Jeffrey Jones Walter J. Scheirer 297 16 0 25 Sep 2023
The Hydra Effect: Emergent Self-repair in Language Model Computations Tom McGrath Matthew Rahtz János Kramár Vladimir Mikulik Shane Legg MILM LRM 214 91 0 28 Jul 2023
Scale Alone Does not Improve Mechanistic Interpretability in Vision ModelsNeural Information Processing Systems (NeurIPS), 2023 Roland S. Zimmermann Thomas Klein Wieland Brendel 264 23 0 11 Jul 2023
Don't trust your eyes: on the (un)reliability of feature visualizationsInternational Conference on Machine Learning (ICML), 2023 Robert Geirhos Roland S. Zimmermann Blair Bilodeau Wieland Brendel Been Kim FAtt OOD 452 36 0 07 Jun 2023
Language Models Implement Simple Word2Vec-style Vector ArithmeticNorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 Jack Merullo Carsten Eickhoff Ellie Pavlick KELM 285 85 0 25 May 2023
Causal Analysis for Robust Interpretability of Neural NetworksIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 Ola Ahmad Nicolas Béreux Loïc Baret V. Hashemi Freddy Lecue CML 301 10 0 15 May 2023
Why is plausibility surprisingly problematic as an XAI criterion? Weina Jin Xiaoxiao Li Ghassan Hamarneh 347 10 0 30 Mar 2023
The Representational Status of Deep Learning Models Eamon Duede 272 3 0 21 Mar 2023
Tracr: Compiled Transformers as a Laboratory for InterpretabilityNeural Information Processing Systems (NeurIPS), 2023 David Lindner János Kramár Sebastian Farquhar Matthew Rahtz Tom McGrath Vladimir Mikulik 474 87 0 12 Jan 2023
Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance Kenzo Clauw S. Stramaglia Daniele Marinazzo SSL FAtt 192 8 0 01 Nov 2022
SoK: Explainable Machine Learning for Computer Security ApplicationsEuropean Symposium on Security and Privacy (Euro S&P), 2022 A. Nadeem D. Vos Clinton Cao Luca Pajola Simon Dieck Robert Baumgartner S. Verwer 342 63 0 22 Aug 2022
Do We Need Another Explainable AI Method? Toward Unifying Post-hoc XAI Evaluation Methods into an Interactive and Multi-dimensional Benchmark Mohamed Karim Belaid Eyke Hüllermeier Maximilian Rabus Ralf Krestel ELM 161 0 0 08 Jun 2022
Additive MIL: Intrinsically Interpretable Multiple Instance Learning for PathologyNeural Information Processing Systems (NeurIPS), 2022 Syed Ashar Javed Dinkar Juyal Harshith Padigela A. Taylor-Weiner Limin Yu Aaditya (Adi) Prakash 188 85 0 03 Jun 2022
Attribution-based Explanations that Provide Recourse Cannot be RobustJournal of machine learning research (JMLR), 2022 H. Fokkema R. D. Heide T. Erven FAtt 350 22 0 31 May 2022
Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI Greta Warren Mark T. Keane R. Byrne CML 145 27 0 21 Apr 2022
An explainability framework for cortical surface-based deep learning Fernanda L. Ribeiro S. Bollmann R. Cunnington A. M. Puckett FAtt AAML MedIm 134 3 0 15 Mar 2022
Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscienceArtificial Intelligence for the Earth Systems (AI4ES), 2022 Antonios Mamalakis E. Barnes I. Ebert‐Uphoff 224 88 0 07 Feb 2022
Framework for Evaluating Faithfulness of Local ExplanationsInternational Conference on Machine Learning (ICML), 2022 S. Dasgupta Nave Frost Michal Moshkovitz FAtt 400 78 0 01 Feb 2022
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIACM Computing Surveys (ACM CSUR), 2022 Meike Nauta Jan Trienes Shreyasi Pathak Elisa Nguyen Michelle Peters Yasmin Schmitt Jorg Schlotterer M. V. Keulen C. Seifert ELM XAI 563 555 0 20 Jan 2022
HIVE: Evaluating the Human Interpretability of Visual ExplanationsEuropean Conference on Computer Vision (ECCV), 2021 Sunnie S. Y. Kim Nicole Meister V. V. Ramaswamy Ruth C. Fong Olga Russakovsky 382 130 0 06 Dec 2021
Acquisition of Chess Knowledge in AlphaZero Thomas McGrath A. Kapishnikov Nenad Tomašev Adam Pearce Demis Hassabis Been Kim Ulrich Paquet Vladimir Kramnik 405 188 0 17 Nov 2021
Grounding Representation Similarity with Statistical Testing Frances Ding Jean-Stanislas Denain Jacob Steinhardt 200 32 0 03 Aug 2021
How Well do Feature Visualizations Support Causal Understanding of CNN Activations? Roland S. Zimmermann Judy Borowski Robert Geirhos Matthias Bethge Thomas S. A. Wallis Wieland Brendel FAtt 292 39 0 23 Jun 2021
The effectiveness of feature attribution methods and its correlation with automatic evaluation scoresNeural Information Processing Systems (NeurIPS), 2021 Giang Nguyen Daeyoung Kim Anh Totti Nguyen FAtt 463 104 0 31 May 2021
XAI Handbook: Towards a Unified Framework for Explainable AI Sebastián M. Palacio Adriano Lucieri Mohsin Munir Jörn Hees Sheraz Ahmed Andreas Dengel 125 40 0 14 May 2021
Leveraging Sparse Linear Layers for Debuggable Deep NetworksInternational Conference on Machine Learning (ICML), 2021 Eric Wong Shibani Santurkar Aleksander Madry FAtt 188 96 0 11 May 2021
Two4Two: Evaluating Interpretable Machine Learning - A Synthetic Dataset For Controlled Experiments M. Schuessler Philipp Weiß Leon Sixt 147 3 0 06 May 2021
Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark DatasetEnvironmental Data Science (EDS), 2021 Antonios Mamalakis I. Ebert‐Uphoff E. Barnes OOD 343 87 0 18 Mar 2021
If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI TechniquesInternational Joint Conference on Artificial Intelligence (IJCAI), 2021 Mark T. Keane Eoin M. Kenny Eoin Delaney Barry Smyth CML 278 165 0 26 Feb 2021