# Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment

arXiv: https://arxiv.org/abs/2602.16660 · HTML: https://mlsanity.com/paper/2602.16660/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 43 of its 52 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 43)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Safety Alignment Should Be Made More Than Just a Few Tokens Deep](https://mlsanity.com/paper/2406.05946/) (2024)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://mlsanity.com/paper/2402.16438/) (2024)
- [Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs](https://mlsanity.com/paper/2305.16339/) (2023)
- [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://mlsanity.com/paper/1702.03859/) (2017)
- [LLaMA Beyond English: An Empirical Study on Language Capability Transfer](https://mlsanity.com/paper/2401.01055/) (2024)
- [The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts](https://mlsanity.com/paper/2401.13136/) (2024)
- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)
- [MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization](https://mlsanity.com/paper/2401.06838/) (2024)
- [The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities](https://mlsanity.com/paper/2411.04986/) (2024)
- [All Languages Matter: On the Multilingual Safety of Large Language Models](https://mlsanity.com/paper/2310.00905/) (2023)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages](https://mlsanity.com/paper/2402.12204/) (2024)
- [Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment](https://mlsanity.com/paper/2311.08089/) (2023)

## Built on by (most cited first, 9 of 9)

- [Multilingual Safety Alignment via Self-Distillation](https://mlsanity.com/paper/2605.02971/) (2026)
- [Low-Resource Safety Failures Are Action Failures, Not Representation Failures](https://mlsanity.com/paper/2606.01196/) (2026)
- [Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models](https://mlsanity.com/paper/2606.08451/) (2026)
- [Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry](https://mlsanity.com/paper/2606.13934/) (2026)
- [One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs](https://mlsanity.com/paper/2607.27917/) (2026)
- [LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2608.14626/) (2026)
- [Latent Space Refusal Anchoring for Low-Resource African Languages: Mechanistic Safety Recovery Without Retraining](https://mlsanity.com/paper/2608.18089/) (2026)
- [When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs](https://mlsanity.com/paper/2608.29936/) (2026)
- [Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs](https://mlsanity.com/paper/2609.22144/) (2026)

## Abstract (arXiv)

The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require substantial resources, either through large-scale, high-quality supervision in the target language or through pairwise alignment with high-resource languages, which limits scalability. In this work, we propose a resource-efficient method for improving multilingual safety alignment. We introduce a plug-and-play Multi-Lingual Consistency (MLC) loss that can be integrated into existing monolingual alignment pipelines. By improving collinearity between multilingual representation vectors, our method encourages directional consistency at the multilingual semantic level in a single update. This allows simultaneous alignment across multiple languages using only multilingual prompt variants without requiring additional response-level supervision in low-resource languages. We validate the proposed method across different model architectures and alignment paradigms, and demonstrate its effectiveness in enhancing multilingual safety with limited impact on general model utility. Further evaluation across languages and tasks indicates improved cross-lingual generalization, suggesting the proposed approach as a practical solution for multilingual consistency alignment under limited supervision.