3 papers
cs.GT2026
Dimensions of Power: A Systematic Guide to Power Indices for Explainable AI
Filip Naudot, Arunavo Ganguly, Timotheus Kampik +2
Power indices, originating in cooperative game theory, quantify each player's influence on the outcome of a given game. Originally designed to distribute profits or costs among pla…
cs.AI2026
Set Contribution Functions for Quantitative Bipolar Argumentation and their Principles
Filip Naudot, Andreas Brännström, Vicenç Torra +1
We present functions that quantify the contribution of a set of arguments in quantitative bipolar argumentation graphs to (the final strength of) an argument of interest, a so-call…
cs.AI2025
llmSHAP: A Principled Approach to LLM Explainability
Filip Naudot, Tobias Sundqvist, Timotheus Kampik
Feature attribution methods help make machine learning-based inference explainable by determining how much one or several features have contributed to a model's output. A particula…