paper-with-me

Papers

MPO: Multilingual Safety Alignment via Reward Gap Optimization

2025-05-22 · Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across diverse linguistic contexts. Existing preference learning methods for safety alignment, such as RLHF and DPO, are primarily monolingual and struggle with noisy multilingual data. To address these limitations, we introduce Multilingual reward gaP Optimization (MPO), a novel approach that leverages the well-aligned safety capabilities of the dominant language (English) to improve safety alignment across multiple languages. MPO directly minimizes the reward gap difference between the dominant language and target languages, effectively transferring safety capabilities while preserving the original strengths of the dominant language. 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.

📄 PDF Abstract BibTeX arXiv:2505.16869

Code (1)

circle-hit/mpo 공식 구현 pytorch

Tasks

Safety Alignment

Methods 이 논문이 사용한 방법론

DPO 설명 없음

Similar Papers 제목 키워드 기반

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization

2025-11-17 · Xuankun Rong, Wenke Huang, Tingfeng Wang, Daiguo Zhou 외 arxiv

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex…

Multilingual Refusal Alignment for Safer Large Language Models

2026-04-24 · Aleksandra Krasnodębska, Wojciech Kusa, Aldo Lipani arxiv

As Large Language Models (LLMs) are deployed globally, ensuring their safety and alignment across multiple languages becomes paramount. However, safety behaviors often vary unpredictably between languages, posing signifi…

General Knowledge

Stepwise Alignment for Constrained Language Model Policy Optimization

2024-04-17 · Akifumi Wachi, Thien Q. Tran, Rei Sato, Takumi Tanabe 외

Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment as an optimization problem of the langua…

Computational EfficiencyLanguage ModelingLanguage Modellingmodel

Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control

2026-02-07 · Yonghui Yang, Wenjian Tao, Jilong Liu, Xingyu Zhu 외 arxiv

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization…

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment

2025-03-06 · Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong 외

Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual prefe…

Instruction FollowingTransfer Learning