Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?
Yeji Kim, Housam Babiker, Mi-Young Kim +1
Mixture-of-Experts (MoE) architectures have recently been extended with role-based mechanisms for interpretability. This is typically done by assigning semantic roles to individual…
cs.LG2026
Feature-level Interaction Explanations in Multimodal Transformers
Yeji Kim, Housam Khalifa Bashier Babiker, Mi-Young Kim +1
Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multimodal explainable AI (MXAI) methods ext…