1k citations · 1.4k across the 27 of their papers we have counts for
27 papers
Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?
Franka Bause, Jonas Niederle, Martin Pawelczyk +1
The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collaborate. We study this mechanism…
Validity Threats for Foundation Model Research
Gunnar König, Martin Pawelczyk, Ulrike von Luxburg +1
Controlled experiments are the backbone of machine learning research, but at the scale of modern foundation models, they have become prohibitively expensive. Instead, the community…
Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks
Samira Abedini, Sina Mavali, Lea Schönherr +2
Large Language Model (LLM)-based Multi-Agent Systems (MASs) are increasingly deployed for agentic tasks, such as web automation, itinerary planning, and collaborative problem solvi…
Easy Data Unlearning Bench
Roy Rinberg, Pol Puigdemont, Martin Pawelczyk +1
Evaluating machine unlearning methods remains technically challenging, with recent benchmarks requiring complex setups and significant engineering overhead. We introduce a unified…
Train Once, Answer All: Many Pretraining Experiments for the Cost of One
Sebastian Bordt, Martin Pawelczyk
Recent work has demonstrated that controlled pretraining experiments are a powerful tool for studying the relationship between training data and large language model (LLM) behavior…
Efficiently Verifiable Proofs of Data Attribution
Ari Karchmer, Martin Pawelczyk, Seth Neel
Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation o…
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
Martin Pawelczyk, Lillian Sun, Zhenting Qi +2
The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong ge…
Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
Catherine Huang, Martin Pawelczyk, Himabindu Lakkaraju
Predictive machine learning models are becoming increasingly deployed in high-stakes contexts involving sensitive personal data; in these contexts, there is a trade-off between mod…
Machine Unlearning Fails to Remove Data Poisoning Attacks
Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu +3
We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion request…
Towards Non-Adversarial Algorithmic Recourse
Tobias Leemann, Martin Pawelczyk, Bardh Prenkaj +1
The streams of research on adversarial examples and counterfactual explanations have largely been growing independently. This has led to several recent works trying to elucidate th…
In-Context Unlearning: Language Models as Few Shot Unlearners
Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju
Machine unlearning, the study of efficiently removing the impact of specific training instances on a model, has garnered increased attention in recent years due to regulatory guide…
Gaussian Membership Inference Privacy
Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
We propose a novel and practical privacy notion called -Membership Inference Privacy (-MIP), which explicitly considers the capabilities of realistic adversaries under the me…
On the Privacy Risks of Algorithmic Recourse
Martin Pawelczyk, Himabindu Lakkaraju, Seth Neel
As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to…
Decomposing Counterfactual Explanations for Consequential Decision Making
Martin Pawelczyk, Lea Tiyavorabun, Gjergji Kasneci
The goal of algorithmic recourse is to reverse unfavorable decisions (e.g., from loan denial to approval) under automated decision making by suggesting actionable feature changes (…
I Prefer not to Say: Protecting User Consent in Models with Optional Personal Data
Tobias Leemann, Martin Pawelczyk, Christian Thomas Eberle +1
We examine machine learning models in a setup where individuals have the choice to share optional personal information with a decision-making system, as seen in modern insurance pr…
Language Models are Realistic Tabular Data Generators
Vadim Borisov, Kathrin Seßler, Tobias Leemann +2
Tabular data is among the oldest and most ubiquitous forms of data. However, the generation of synthetic samples with the original data's characteristics remains a significant chal…
On the Trade-Off between Actionable Explanations and the Right to be Forgotten
Martin Pawelczyk, Tobias Leemann, Asia Biega +1
As machine learning (ML) models are increasingly being deployed in high-stakes applications, policymakers have suggested tighter data protection regulations (e.g., GDPR, CCPA). One…
OpenXAI: Towards a Transparent Evaluation of Model Explanations
Chirag Agarwal, Dan Ley, Satyapriya Krishna +6
While several types of post hoc explanation methods have been proposed in recent literature, there is very little work on systematically benchmarking these methods. Here, we introd…
Rethinking Stability for Attribution-based Explanations
Chirag Agarwal, Nari Johnson, Martin Pawelczyk +4
As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are st…
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
Martin Pawelczyk, Teresa Datta, Johannes van-den-Heuvel +2
As machine learning models are increasingly being employed to make consequential decisions in real-world settings, it becomes critical to ensure that individuals who are adversely…
Deep Neural Networks and Tabular Data: A Survey
Vadim Borisov, Tobias Leemann, Kathrin Seßler +3
Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous data sets, dee…
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Martin Pawelczyk, Sascha Bielawski, Johannes van den Heuvel +2
Counterfactual explanations provide means for prescriptive model explanations by suggesting actionable feature changes (e.g., increase income) that allow individuals to achieve fav…
Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis
Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi +2
As machine learning (ML) models become more widely deployed in high-stakes applications, counterfactual explanations have emerged as key tools for providing actionable model explan…
Gaussian Experts Selection using Graphical Models
Hamed Jalali, Martin Pawelczyk, Gjergji Kasneci
Local approximations are popular methods to scale Gaussian processes (GPs) to big data. Local approximations reduce time complexity by dividing the original dataset into subsets an…