paper-with-me

Papers

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 significant challenges for consistent and ethical AI. In this work, we systematically investigate the dynamics of multilingual alignment, exploring whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities. We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models. Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.

📄 PDF Abstract BibTeX arXiv:2606.07535

Code (0)

등록된 구현이 없습니다.

Tasks

General Knowledge

Similar Papers 제목 키워드 기반

Refusal Behavior in Large Language Models: A Nonlinear Perspective

2025-01-14 · Fabian Hildebrandt, Andreas Maier, Patrick Krauss, Achim Schilling

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior acr…

Dimensionality Reduction

Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models

2026-06-02 · Hashmat Shadab Malik, Muzammal Naseer, Salman Khan arxiv

Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial attacks. Prior work on MLLM robustness has focused largely on Engli…

Adversarial Robustness

Steering Over-refusals Towards Safety in Retrieval Augmented Generation

2025-10-12 · Utsav Maskey, Mark Dras, Usman Naseem arxiv

Safety alignment in large language models (LLMs) induces over-refusals -- where LLMs decline benign requests due to aggressive safety filters. We analyze this phenomenon in retrieval-augmented generation (RAG), where bot…

BabelSteering: Multilingual Safety Alignment via English Steering Vectors

2026-08-17 · Emma V. Stein, Dominik Meier, Terry Ruas, Jan Philip Wahle 외 arxiv

Large language models (LLMs) are deployed globally in high-stakes settings, yet most safety research and alignment efforts remain concentrated on English. Thus, users interacting with LLMs in other languages may encounte…

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

2024-09-01 · Bang An, Sicheng Zhu, Ruiyi Zhang, Michael-Andrei Panaitescu-Liess 외

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a…