Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Existing preference learning methods for safety alignment are monolingual and struggle with noisy multilingual data. |
| Approach: | They propose a multilingual reward gaP optimization approach that leverages the well-aligned safety capabilities of the dominant language to improve safety alignment across multiple languages. |
| Outcome: | Extensive experiments on three LLMs, LLaMA-3.1, Gemma-2 and Qwen2.5, validate MPO’s efficacy in multilingual safety alignment without degrading general multilingual utility. |
Similar Papers
Multilingual Refusal Alignment for Safer Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used globally, but their safety and alignment can vary unpredictably between languages. |
| Approach: | They propose a multilingual refusal alignment dataset to investigate whether alignment transfers cross-lingually and how language consistency is preserved during training. |
| Outcome: | The proposed model can be trained on multilingual datasets without affecting general performance. |
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts (2024.findings-acl)
Copied to clipboard
Lingfeng Shen, Weiting Tan, Sihao Chen, Yunmo Chen, Jingyu Zhang, Haoran Xu, Boyuan Zheng, Philipp Koehn, Daniel Khashabi
| Challenge: | Recent studies show that malicious prompt instructions could solicit objectionable content from LLMs. |
| Approach: | They compare how state-of-the-art LLMs respond to malicious prompts in different languages . they find that LLM's generate unsafe responses more often when a prompt is written in a lower-resource language . |
| Outcome: | The proposed model can generate unsafe responses more often when a malicious prompt is written in a lower-resource language, and less irrelevant responses when written in lower-source languages. |
Multilingual Blending: Large Language Model Safety Alignment Evaluation with Language Mixture (2025.findings-naacl)
Copied to clipboard
| Challenge: | a range of representative Large Language Models have exhibited remarkable generalization capabilities across numerous downstream tasks. |
| Approach: | They propose a query-response scheme to evaluate the safety alignment of LLMs . they found that multilingual query-responding significantly amplifies the detriment of malicious queries . |
| Outcome: | The proposed scheme improves the safety alignment of state-of-the-art LLMs under multilingual conditions. |
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment (2026.findings-acl)
Copied to clipboard
Iago Alves Brito, Walcy Rios, Julia Soares Dollis, Diogo Fernandes Costa Silva, Arlindo Rodrigues Galvão Filho
| Challenge: | Existing safety evaluations of large language models aggregate harms under generic categories such as "Identity Hate" a bilingual benchmark identifies a selective safety trap, where defense rates vary by up to 42% within the same model solely based on the target group. |
| Approach: | They propose a bilingual adversarial benchmark to audit selective safety in large language models . defense rates vary by up to 42% within the same model solely based on target group . |
| Outcome: | The proposed benchmark identifies a selective safety trap in large language models . defense rates vary by up to 42% within the same model solely based on the target group. |
The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm (2024.emnlp-main)
Copied to clipboard
null Aakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant, Julia Kreutzer, Marzieh Fadaee, Sara Hooker
| Challenge: | Existing approaches to safety alignment focus on homogeneous monolingual settings . preference training and safety measures often overfit to harms common in Western-centric datasets . |
| Approach: | They propose to use human annotated red teaming prompts to identify global and local harms. |
| Outcome: | The proposed approach can address and optimize for a non-homogeneous set of languages and cultural preferences while minimizing both global and local harms. |
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Preference optimization is a widely adopted post-training technique to align large language models with human preferences. |
| Approach: | They propose a method for generating multilingual feedback data to balance data coverage. |
| Outcome: | The proposed method achieves 54.4% win-rate against current state-of-the-art multilingual LLM in its parameter class and 69.5% win- rate or higher against widely used models like Gemma, Mistral and Llama 3. |
CM-Align: Consistency-based Multilingual Alignment for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current large language models (LLMs) show a significant performance gap in alignment between English and other languages. |
| Approach: | They propose a consistency-based method to construct high-quality multilingual preference data for improving multilingual alignment. |
| Outcome: | The proposed method is based on three LLMs and three common tasks and shows that it performs better than current methods. |
The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It (2025.emnlp-main)
Copied to clipboard
| Challenge: | a systematic review of 300 publications reveals a language gap in LLM safety research . even high-resource non-English languages receive little attention, authors note . |
| Approach: | They propose to focus on safety evaluation, training data generation, and crosslingual safety generalization based on their findings. |
| Outcome: | The authors suggest that the field can develop more robust, inclusive safety practices for diverse global populations. |
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have sparked concerns about their safety. |
| Approach: | They propose a method to identify safety-related information in the model parameter space . they propose to use a few adversarially chosen examples to fine-tune LLMs . |
| Outcome: | The proposed method can break safety alignment in multilingual LLMs using a few examples . it also shows that the proposed method jailbreaks LLM models adapted to new languages . |
Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Existing safety alignment methods for Large Language Models (LLMs) face the distribution shift issue, which requires significant computational resources. |
| Approach: | They propose a framework that leverages the model’s intrinsic safety judgment capability to extract reward signals, which are then used to calculate label confidence for preference reordering. |
| Outcome: | The proposed framework improves safety performance while avoiding 300x computational overheads. |