相关论文: Bridging the Multilingual Safety Divide: Efficient…

Artificial Intelligence (AI)-driven code generation tools are increasingly used throughout the software development lifecycle to accelerate coding tasks. However, the security of AI-generated code using Large Language Models (LLMs) remains…

Based on the foundation of Large Language Models (LLMs), Multilingual LLMs (MLLMs) have been developed to address the challenges faced in multilingual natural language processing, hoping to achieve knowledge transfer from high-resource…

Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not…

Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture-independent…

Large Language Models (LLMs) have shown strong performance across many tasks, but their ability to capture culturally diverse moral values remains unclear. In this paper, we examine whether LLMs mirror variations in moral attitudes reported…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Large reasoning models (LRMs) have demonstrated impressive performance across a range of reasoning tasks, yet little is known about their internal reasoning processes in multilingual settings. We begin with a critical question: {\it In…

As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in static evaluation settings, face two major limitations in…

Large language models (LLMs) are increasingly deployed for everyday tasks, including food preparation and health-related guidance. However, food safety remains a high-stakes domain where inaccurate or misleading information can cause severe…

As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe outputs and guide safety, but such connections with safety are…

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as…

Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-resource languages,…

Providing better language tools for low-resource and endangered languages is imperative for equitable growth. Recent progress with massively multilingual pretrained models has proven surprisingly effective at performing zero-shot transfer…

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater.…

RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has…

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…

Recent advancements in large language models (LLMs) have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies primarily focus on…

Multilingual LLMs often have knowledge disparities across languages, with larger gaps in under-resourced languages. Teaching LLMs to abstain in the face of knowledge gaps is thus a promising strategy to mitigate hallucinations in…