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

arXiv 2606.13709•94532acd124ce02bfdbd49ffe47eb92fd41da4dd4346655ec74da0161a38a9e1
ANTSBregman-divergenceHSIC','sensitivity-analysis','aleatory-epistemic','uncertainty-#Hermite-decompositionLoMCarxivdecision-treesdiffusion-modelsdomain-adaptatione-valuesfoundation-modelslabel-shiftlong-form-reasoningmachine-learningmodel-collapsemodel-editingmodel-safetynucleus-truncationoptimal-transportrecursive-trainingrefusal-suppressionrouted-MoEsamplingsequential-testingspectral-analysis

Paper metadata

arXiv ID
2606.13709
Version
Not specified by this published record
Category
Statistics — Machine Learning (stat.ML)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_stat_ml
Record identifier
94532acd124ce02bfdbd49ffe47eb92fd41da4dd4346655ec74da0161a38a9e1
Enrichment time
2026-06-15T07:23:56Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.