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. |
Similar Papers
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. |
Safety of Large Language Models Beyond English: A Systematic Literature Review of Risks, Biases, and Safeguards (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have a growing number of applications that generate harmful, biased, or unsafe content. |
| Approach: | They synthesize findings from recent studies that evaluate their robustness across languages . they highlight gaps in multilingual safety research and recommend future work . |
| Outcome: | The systematic review examines the multilingual safety of large language models in English . it identifies challenges such as dataset availability and evaluation biases . |
All Languages Matter: On the Multilingual Safety of LLMs (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. |
| Approach: | They propose a prompting method to improve multilingual safety of ChatGPT by enhancing cross-lingual generalization of safety alignment. |
| Outcome: | The proposed method can significantly reduce the ratio of unsafe responses by 42% for non-English queries. |
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. |
SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)
Copied to clipboard
Chuxue Cao, Han Zhu, Jiaming Ji, Qichao Sun, Zhenghao Zhu, Wu Yinyu, Josef Dai, Yaodong Yang, Sirui Han, Yike Guo
| Challenge: | Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations. |
| Approach: | They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark. |
| Outcome: | The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks. |
Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety (2026.eacl-srw)
Copied to clipboard
Denis Janiak, Julia Moska, Dawid Motyka, Karolina Seweryn, Paweł Walkowiak, Bartosz Żuk, Arkadiusz Janz
| Challenge: | Existing studies focus on individual techniques or specific dimensions, lacking a holistic assessment of the inherent trade-offs. |
| Approach: | They propose a framework that compares LLM alignment methods across five axes . they use a validated LLM-as-judge prompt to compare the results . |
| Outcome: | The proposed framework compares LLM alignment methods across factuality, safety, conciseness, proactivity, diversity and safety axes . it provides insights into trade-offs of common alignment methods, guiding the development of more balanced and reliable LLMs. |
Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding (2025.acl-long)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) are inherently multilingual agents . concerns regarding their safety have emerged . |
| Approach: | They propose a framework to synthesize red-teaming queries and investigate their safety . they demonstrate that the framework outperforms existing red- teaming techniques . |
| Outcome: | The proposed framework outperforms existing red-teaming techniques in the safety domain . it generates code-switching attack prompts in monolingual data . |
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 . |
AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual large language models (LLMs) possess impressive multilingual understanding and generation capabilities, but performance and cross-lingual alignment often lag for non-dominant languages. |
| Approach: | They propose a representation-level framework to enhance multilingual performance of pre-trained LLMs by integrating multilingual semantic alignment and language feature integration. |
| Outcome: | The proposed framework improves multilingual capability of pre-trained LLMs by bringing representations closer and improving cross-lingual alignment. |
MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)
Copied to clipboard
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. |