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.

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.
MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)

Copied to clipboard

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.
Understanding Cross-Lingual Alignment—A Survey (2024.findings-acl)

Copied to clipboard

Challenge: Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models.
Approach: They propose a taxonomy of methods to improve cross-lingual alignment . they argue that an effective trade-off between language-neutral and language-specific information is key .
Outcome: The proposed methods can be applied to encoder models and encoder-decoder-only models . they show that language-neutral and language-specific information is key .
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment (2025.findings-emnlp)

Copied to clipboard

Challenge: Soteria locates and minimally adjusts the “functional heads” most responsible for harmful content generation in each language.
Approach: Soteria locates and minimally adjusts the "functional heads" responsible for harmful content generation in each language.
Outcome: The proposed approach reduces harmful content generation in languages while preserving model performance.
From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models (2024.findings-acl)

Copied to clipboard

Challenge: toxicity mitigation in language models has been focused on single-language settings . however, widespread adoption of LLMs has introduced a range of unknown -harms .
Approach: They employ translated data to evaluate and enhance mitigation techniques in the absence of sufficient annotated datasets across languages.
Outcome: The proposed approach compares translation quality and retrieval-augmented mitigation techniques under static and continual toxicity mitigation scenarios.
A Survey of Toxicity Mitigation Strategies for Multilingual Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models can reproduce and amplify toxic content, including hate speech, harassment, and bias.
Approach: They propose a comprehensive survey of the many detoxification methods tailored to multilingual LLMs.
Outcome: The proposed methods are based on data filtering, style transfer, expert-based logit steering, retrieval augmentation, and human feedback.
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment (2026.findings-acl)

Copied to clipboard

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 Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts (2024.findings-acl)

Copied to clipboard

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.
Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? (2024.findings-emnlp)

Copied to clipboard

Challenge: Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English.
Approach: They extend previous research that shows certain abstract concepts are linearly represented as directions in LLMs, predominantly centered around English.
Outcome: The proposed model can be used to align LLMs with human values, and it can generate toxic, untruthful, biased, and even illegal content.
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations