AINeutralarXiv – CS AI · 6h ago6/10
🧠
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Researchers demonstrate that calibration—aligning model confidence with actual accuracy—behaves differently in mixture-of-experts (MoE) models depending on routing mechanisms. While expert-level calibration suffices for hard-routed models under distribution shift, soft-routed models require additional adversarial reweighting techniques to maintain both accuracy and calibration reliability.