Metraipolis › archive › dc_c5ee055aceeb
LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review — arXiv:2608.14626
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14626
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:51:20.238Z
- SHA-256 of the archived text
36621df2588601f6276b7cc0c9ba3e97dcc3a2b9d921529a3771669016256833- Stable URL of this page
https://metraipolis.com/documento/dc_c5ee055aceeb
How to cite
LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review — arXiv:2608.14626 — arXiv (en), https://arxiv.org/abs/2608.14626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5ee055aceeb (Metraipolis archive dc_c5ee055aceeb, sha256 36621df2588601f6276b7cc0c9ba3e97dcc3a2b9d921529a3771669016256833)
BibTeX
@misc{dcc5ee055aceeb,
title = {LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review — arXiv:2608.14626},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14626},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5ee055aceeb; sha256 36621df2588601f6276b7cc0c9ba3e97dcc3a2b9d921529a3771669016256833},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-resource and multilingual settings than in high-resource languages. In this paper, we conduct a Systematic Literature Review (SLR) of LLM safety alignment in low-resource languages by adopting the PRISMA 2020 methodology. Out of roughly 1,500 papers identified from Semantic Scholar, arXiv, and OpenAlex, 50 relevant studies have been selected and analyzed. Our review is organized around four themes: safety alignment methods, multilingual safety risks, evaluation benchmarks, and cross-lingual transferability. We further propose a taxonomy of safety alignment approaches based on three adaptation mechanisms: data adaptation, objective optimization, and mechanistic alignment. Across literature, translated English benchmarks fail to sufficiently represent culturally rooted harms, and multilingual models are more vulnerable to cross-lingual jailbreaks, code-switching attacks, and safety degradation in underrepresented languages. These failures are driven by several key factors, including uneven multilingual pre-training coverage, insufficient native-language preference data, poor transfer of safety representations, and a lack of culturally aware evaluation frameworks. The review also notes that many low-resource languages, especially African languages, have fewer safety benchmarks available than other multilingual regions. Overall, the results reveal a persistent multilingual safety gap, and suggest that future progress will require culturally grounded benchmarks, participatory data collection, balanced multilingual pre-training, and scalable multilingual alignment methods. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.14626 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:13.916Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).