English
Related papers

Related papers: Multilingual Safety Alignment Via Sparse Weight Ed…

200 papers

We introduce a lightweight yet highly effective safety guardrail framework for language models, demonstrating that small-scale language models can achieve, and even surpass, the performance of larger counterparts in content moderation…

Machine Learning · Computer Science 2025-07-14 Aleksei Ilin , Gor Matevosyan , Xueying Ma , Vladimir Eremin , Suhaa Dada , Muqun Li , Riyaaz Shaik , Haluk Noyan Tokgozoglu

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…

Artificial Intelligence · Computer Science 2025-09-08 Tiansheng Huang , Gautam Bhattacharya , Pratik Joshi , Josh Kimball , Ling Liu

Achieving the effective design and improvement of reward functions in reinforcement learning (RL) tasks with complex custom environments and multiple requirements presents considerable challenges. In this paper, we propose ERFSL, an…

Machine Learning · Computer Science 2026-05-19 Guanwen Xie , Jingzehua Xu , Yiyuan Yang , Yimian Ding , Shuai Zhang

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Xingyu Zhu , Beier Zhu , Junfeng Fang , Shuo Wang , Yin Zhang , Xiang Wang , Xiangnan He

Large language models (LLMs) have a transformative impact on a variety of scientific tasks across disciplines including biology, chemistry, medicine, and physics. However, ensuring the safety alignment of these models in scientific research…

The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely on resource-intensive fine-tuning (FT), which may suffer from…

Computation and Language · Computer Science 2025-09-11 Birong Pan , Yongqi Li , Weiyu Zhang , Wenpeng Lu , Mayi Xu , Shen Zhou , Yuanyuan Zhu , Ming Zhong , Tieyun Qian

Despite advances in multilingual capabilities, most large language models (LLMs) remain English-centric in their training and, crucially, in their production of reasoning traces. Even when tasked with non-English problems, these models…

Computation and Language · Computer Science 2026-04-15 Daniil Gurgurov , Tom Röhr , Sebastian von Rohrscheidt , Josef van Genabith , Alexander Löser , Simon Ostermann

This paper examines the problem of adapting neural machine translation systems to new, low-resourced languages (LRLs) as effectively and rapidly as possible. We propose methods based on starting with massively multilingual "seed models",…

Computation and Language · Computer Science 2018-08-14 Graham Neubig , Junjie Hu

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Cryptography and Security · Computer Science 2026-02-19 Jean-Charles Noirot Ferrand , Yohan Beugin , Eric Pauley , Ryan Sheatsley , Patrick McDaniel

Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, when a problem requires incorporating information from multiple datasets - as in…

Machine Learning · Computer Science 2026-04-03 Liyi Zhang , Jake Snell , Thomas L. Griffiths

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to…

Machine Learning · Computer Science 2025-06-25 Shuang Ao , Yi Dong , Jinwei Hu , Sarvapali Ramchurn

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Computation and Language · Computer Science 2025-06-03 Danni Liu , Jan Niehues

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Machine Learning · Computer Science 2026-02-11 Jonathan Svirsky , Yehonathan Refael , Ofir Lindenbaum

Large language models (LLMs) that are tuned with instructions have demonstrated remarkable capabilities in various tasks and languages. However, their ability to generalize to underrepresented languages is limited due to the scarcity of…

Computation and Language · Computer Science 2023-10-25 Samuel Cahyawijaya , Holy Lovenia , Tiezheng Yu , Willy Chung , Pascale Fung

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

As Large Language Models (LLMs) receive increasing attention and are being deployed across various domains, their potential risks, including generating harmful or biased content, producing unsupported claims, and exhibiting vulnerabilities…

Computation and Language · Computer Science 2026-04-20 Wai Man Si , Mingjie Li , Michael Backes , Yang Zhang

When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO,…

Artificial Intelligence · Computer Science 2026-01-01 Lijun Zhang , Lin Li , Wei Wei , Yajie Qi , Huizhong Song , Jun Wang , Yaodong Yang , Jiye Liang

This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We selected open source models based on the most common alignment methods, namely, Supervised…

Knowledge editing aims to change language models' performance on several special cases (i.e., editing scope) by infusing the corresponding expected knowledge into them. With the recent advancements in large language models (LLMs), knowledge…

Computation and Language · Computer Science 2024-05-31 Jiaan Wang , Yunlong Liang , Zengkui Sun , Yuxuan Cao , Jiarong Xu , Fandong Meng

Ensuring consistent safety across multiple languages remains a significant challenge for large language models (LLMs). We introduce Soteria, a lightweight yet powerful strategy that locates and minimally adjusts the "functional heads" most…

Computation and Language · Computer Science 2025-08-25 Somnath Banerjee , Sayan Layek , Pratyush Chatterjee , Animesh Mukherjee , Rima Hazra