4 papers
FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora
Lars Henry Berge Olsen, Pierre Lison, Martin Jullum +1
FindMyText is an open‑source Python tool that efficiently checks whether a given text appears, fully or partially, in large web‑crawled corpora by using fingerprint chains to detec…
Computing Conditional Shapley Values Using Tabular Foundation Models
Lars Henry Berge Olsen, Dennis Christensen
Shapley values have become a cornerstone of explainable AI, but they are computationally expensive to use, especially when features are dependent. Evaluating them requires approxim…
shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Python
Martin Jullum, Lars Henry Berge Olsen, Jon Lachmann +1
This paper introduces the shapr R package, a versatile tool for generating Shapley value-based prediction explanations for machine learning and statistical regression models. Moreo…
Improving the Weighting Strategy in KernelSHAP
Lars Henry Berge Olsen, Martin Jullum
In Explainable AI (XAI), Shapley values are a popular model-agnostic framework for explaining predictions made by complex machine learning models. The computation of Shapley values…