arXiv Machine Learning By Yan Hong, Kedong Xiu, Wei Li, Jun Lan, Huijia Zhu, Shuheng Zhou, Zhongcai Lyu, Weiqiang Wang, Jianfu Zhang

LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models

Read the original on arXiv Machine Learning →

arXiv:2606. 13709v1 Announce Type: cross Abstract: We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving general capability under a compact intervention footprint.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.