Is Refusal Direction Universal across Low-Resourced Languages?
arXiv:2610.28897v1 Announce Type: new Abstract: Refusal directions have been shown to transfer cross-lingually with near-perfect effectiveness across safety-aligned languages (Wang et al., 2025), reportedly regardless of resource level. However, the only truly low-resourced language evaluated is Yo…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv cs.CL
Is Refusal Direction Universal across Low-Resourced Languages?