1 citations · 1 across the 6 of their papers we have counts for
6 papers
VARSHAP: Addressing Global Dependency Problems in Explainable AI with Variance-Based Local Feature Attribution
Mateusz Gajewski, Mikołaj Morzy, Adam Karczmarz +1
Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior. This paper introduces VARSHAP, a novel model-agnos…
EXALT: EXplainable ALgorithmic Tools for Optimization Problems
Zuzanna Bączek, Michał Bizoń, Aneta Pawelec +1
Algorithmic solutions have significant potential to improve decision-making across various domains, from healthcare to e-commerce. However, the widespread adoption of these solutio…
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
Mateusz Olko, Mateusz Gajewski, Joanna Wojciechowska +3
Neural causal discovery methods have recently improved in terms of scalability and computational efficiency. However, our systematic evaluation highlights significant room for impr…
PUB: Plot Understanding Benchmark and Dataset for Evaluating Large Language Models on Synthetic Visual Data Interpretation
Aneta Pawelec, Victoria Sara Wesołowska, Zuzanna Bączek +1
The ability of large language models (LLMs) to interpret visual representations of data is crucial for advancing their application in data analysis and decision-making processes. T…
Dynamic PageRank: Algorithms and Lower Bounds
Rajesh Jayaram, Jakub Łącki, Slobodan Mitrović +2
We consider the PageRank problem in the dynamic setting, where the goal is to explicitly maintain an approximate PageRank vector for a graph under a sequence of…
Accurate estimation of feature importance faithfulness for tree models
Mateusz Gajewski, Adam Karczmarz, Mateusz Rapicki +1
In this paper, we consider a perturbation-based metric of predictive faithfulness of feature rankings (or attributions) that we call PGI squared. When applied to decision tree-base…