pith. sign in

The Twelfth International Conference on Learning Representations , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2026 2

clear filters

representative citing papers

Multilingual Safety Alignment via Self-Distillation

cs.LG · 2026-05-03 · unverdicted · novelty 6.0 · 2 refs

MSD enables cross-lingual safety transfer in LLMs via self-distillation with Dual-Perspective Safety Weighting, improving safety in low-resource languages without target response data.

Multilingual Refusal Alignment for Safer Large Language Models

cs.CL · 2026-04-24 · conditional · novelty 5.0

English-only safety alignment fails to transfer cross-lingually, while multilingual DPO training on the new RefusEU dataset improves safety across 12 European languages without degrading Global MMLU performance.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Multilingual Safety Alignment via Self-Distillation cs.LG · 2026-05-03 · unverdicted · none · ref 42 · 2 links

    MSD enables cross-lingual safety transfer in LLMs via self-distillation with Dual-Perspective Safety Weighting, improving safety in low-resource languages without target response data.