MP
Martin Pawelczyk
cs.LGcs.AIcs.CYcs.CRstat.MLcs.CLcs.MA
On Valency
published · living versionsW_gwpr64vn·v1 · currentpublished
Forget What Comes Next: LLM Unlearning via Statistical Independence
with Andrii Shkabrii, Claudia Plant
1 version
W_x8mtzqcb·v1published
Preprints & journals
26 papers in the corpus · 2019–2026Validity Threats for Foundation Model Research2606.05029v1 · Gunnar Konig, Martin Pawelczyk, Ulrike von Luxburg et al.2026 · 0 citationsarXiv
Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?2605.25929v2 · Franka Bause, Jonas Niederle, Martin Pawelczyk et al.2026 · 0 citationsarXiv
Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks2603.15809v1 · Samira Abedini, Sina Mavali, Lea Schonherr et al.2026 · 0 citationsarXiv
Easy Data Unlearning Bench2602.16400v1 · Roy Rinberg, Pol Puigdemont, Martin Pawelczyk et al.2026 · 0 citationsarXiv
Train Once, Answer All: Many Pretraining Experiments for the Cost of One2509.23383v2 · Sebastian Bordt, Martin Pawelczyk2025 · 0 citationsarXiv
Efficiently Verifiable Proofs of Data Attribution2508.10866v2 · Ari Karchmer, Martin Pawelczyk, Seth Neel2025 · 0 citationsarXiv
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models2501.00418v1 · Martin Pawelczyk, Lillian Sun, Zhenting Qi et al.2024 · 0 citationsarXiv
Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference2407.17663v1 · Catherine Huang, Martin Pawelczyk, Himabindu Lakkaraju2024 · 0 citationsarXiv
Machine Unlearning Fails to Remove Data Poisoning Attacks2406.17216v3 · Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu et al.2024 · 0 citationsarXiv
Deep Neural Networks and Tabular Data: A Survey.37015381 · Borisov, Vadim, Leemann, Tobias, Sebler, Kathrin et al.2024 · 1,064 citationsIEEE transactions on neural networks and learning systems. 2024;35(6):7499-7519
Towards Non-Adversarial Algorithmic Recourse2403.10330v1 · Tobias Leemann, Martin Pawelczyk, Bardh Prenkaj et al.2024 · 3 citationsarXiv
In-Context Unlearning: Language Models as Few Shot Unlearners2310.07579v4 · Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju2023 · 20 citationsarXiv
Gaussian Membership Inference Privacy2306.07273v2 · Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci2023 · 1 citationarXiv
On the Privacy Risks of Algorithmic Recourse2211.05427v1 · Martin Pawelczyk, Himabindu Lakkaraju, Seth Neel2022 · 7 citationsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 25-27 April 2023
Decomposing Counterfactual Explanations for Consequential Decision Making2211.02151v1 · Martin Pawelczyk, Lea Tiyavorabun, Gjergji Kasneci2022 · 0 citationsarXiv
I Prefer not to Say: Protecting User Consent in Models with Optional Personal Data2210.13954v5 · Tobias Leemann, Martin Pawelczyk, Christian Thomas Eberle et al.2022 · 1 citationarXiv
Language Models are Realistic Tabular Data Generators2210.06280v2 · Vadim Borisov, Kathrin Se\ssler, Tobias Leemann et al.2022 · 68 citationsarXiv
On the Trade-Off between Actionable Explanations and the Right to be Forgotten2208.14137v3 · Martin Pawelczyk, Tobias Leemann, Asia Biega et al.2022 · 4 citations11th International Conference on Learning Representations (ICLR) 2023
OpenXAI: Towards a Transparent Evaluation of Model Explanations2206.11104v5 · Chirag Agarwal, Dan Ley, Satyapriya Krishna et al.2022 · 112 citationsarXiv
Rethinking Stability for Attribution-based Explanations2203.06877v1 · Chirag Agarwal, Nari Johnson, Martin Pawelczyk et al.2022 · 27 citationsarXiv
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse2203.06768v4 · Martin Pawelczyk, Teresa Datta, Johannes van-den-Heuvel et al.2022 · 16 citations11th International Conference on Learning Representations (ICLR) 2023
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms2108.00783v1 · Martin Pawelczyk, Sascha Bielawski, Johannes van den Heuvel et al.2021 · 36 citations35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks
Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis2106.09992v2 · Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi et al.2021 · 15 citationsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 28-30 March 2022
Gaussian Experts Selection using Graphical Models2102.01496v3 · Hamed Jalali, Martin Pawelczyk, Gjergji Kasneci2021 · 1 citationarXiv
On Counterfactual Explanations under Predictive Multiplicity2006.13132v1 · Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci2020 · 43 citationsProceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), PMLR volume 124, 2020
Learning Model-Agnostic Counterfactual Explanations for Tabular Data1910.09398v2 · Martin Pawelczyk, Johannes Haug, Klaus Broelemann et al.2019 · 167 citationsarXiv
Career total: 38 works. 26 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.