← Back to all news
arXiv Computation and Language By Jiwon Moon, Yerin Hwang, Kyomin Jung

Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs

Read the original on arXiv Computation and Language →

The paper introduces XIH-Bench, a multilingual benchmark for evaluating instruction hierarchy (IH) compliance in large language models across six languages, four domains, and three IH settings. It finds that IH compliance varies with language, showing an asymmetry where a language can strengthen compliance in a higher-priority role but disrupt it in a lower-priority role, and that cross-language conflicts yield higher compliance than same-language conflicts—a phenomenon called the Language Boundary Effect. The study also highlights that language specialization can make lower-priority instructions in favored languages harder to override, raising potential reliability and security concerns.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
3d ago

Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages

The paper investigates how large language models (LLMs) can be bypassed by translating harmful requests from English into low‑resource languages. By testing ten popular LLMs across 79 languages, the authors find that safe English completions often fail to remain safe after translation, with bypass rates between 21.9% and 44.4%. The risk is unevenly distributed across language families and varies significantly between models, making it hard to rank models by safety consistently.

By Jalil Alva, David Harper, Abigail E. Thornton, Rafael S. Villalobos Alva, Leonardo Kenji Minemura Suazo, Konstantinos Karageorgos, Diego Velazquez, Sergio A. Serrano, Marvin Vargas Flores, Aaron Schliem, Fernando F. Migone
llmssafety
More like this →
arXiv AI
Oct 16

Multi-SFT: Permissively-Licensed Multilingual Instruction-Following

Multi‑SFT is a new, commercially permissive dataset comprising 502,818 instruction‑response pairs in five European languages, created through translation and regeneration pipelines to address gaps where simple translation is insufficient. Human evaluation shows strong inter‑annotator agreement (≥0.87) across all languages. Fine‑tuning nine models from three families on Multi‑SFT yields performance competitive with larger, proprietary mixes and official instruction‑tuned releases, especially on safety‑related benchmarks.

By Daniela Baiamonte, Kamyar Zeinalipour, Elena Fano, Stefano Simonazzi, Andrea Zugarini
fine-tuningbenchmarkssafety
More like this →