Skip to content
conftrace_
2026 EMNLP EMNLP 2026

HEAL: Anchored Hyperspherical Equilibrium for Multilingual Safety Alignment

AbstractSafety alignment in large language models is markedly uneven across languages: behaviors learned from English preference data fail to transfer reliably into lower-resource languages, and existing remedies based on per-language preference data or pairwise translation pivots do not scale. We propose Hyperspherical Equilibrium for Aligned Languages (HEAL), a lightweight auxiliary objective that augments any DPO-style alignment pipeline without altering its supervised pairs. HEAL applies two opposing forces to the multilingual representations of the same prompt: a shrink term draws each non-English representation toward a stop-gradient English anchor, while a dilation term repels same-prompt language representations through a pairwise hinge. At equilibrium, representations occupy an English-centered shell-like region that supports cross-lingual transfer while preserving per-language distinctness. Across multiple backbones, HEAL substantially strengthens multilingual safety with the largest gains on the weakest languages, while preserving general capability and showing favorable out-of-distribution behavior on jailbreak evaluation.

More from EMNLP 2026

All EMNLP 2026 papers →