Related papers: SEA-Guard: Culturally Grounded Multilingual Safegu…

Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on general safety and overlook cultural context. In this work, we introduce FanarGuard, a bilingual…

Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm…

As large language models (LLMs) become increasingly prevalent in a wide variety of applications, concerns about the safety of their outputs have become more significant. Most efforts at safety-tuning or moderation today take on a…

Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety frameworks and guardrails, current protective measures exhibit…

The nature of personalized text-to-image models poses a unique safety challenge that generic context-blind methods are ill-equipped to handle. Such global filters create a dilemma: to prevent misuse, they are forced to damage the model's…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

While generative multilingual models are rapidly being deployed, their safety and fairness evaluations are largely limited to resources collected in English. This is especially problematic for evaluations targeting inherently socio-cultural…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

As frontier AI models are deployed globally, it is essential that their behaviour remains safe and reliable across diverse linguistic and cultural contexts. To examine how current model safeguards hold up in such settings, participants from…

The rapid proliferation of AI-generated text online is profoundly reshaping the information landscape. Among various types of AI-generated text, AI-generated news presents a significant threat as it can be a prominent source of…

Artificial Intelligence (AI) has made it possible for anyone to create images, audio, and video with unprecedented ease, enriching education, communication, and creative expression. At the same time, the rapid rise of AI-generated media has…

Multimodal Large Language Models excel in high-resource settings, but often misinterpret long-tail cultural entities and underperform in low-resource languages. To address this gap, we propose a data-centric approach that directly grounds…

Modern moderation systems increasingly support multiple languages, but often fail to address localisation and low-resource variants - creating safety gaps in real-world deployments. Small models offer a potential alternative to large LLMs,…

We present SeaEval, a benchmark for multilingual foundation models. In addition to characterizing how these models understand and reason with natural language, we also investigate how well they comprehend cultural practices, nuances, and…

In the contemporary interconnected world, the concept of cultural responsibility occupies paramount importance. As the lines between nations become less distinct, it is incumbent upon individuals, communities, and institutions to assume the…

Large Language Models (LLMs) have shown remarkable abilities across various tasks, yet their development has predominantly centered on high-resource languages like English and Chinese, leaving low-resource languages underserved. To address…

Recent advances in LLMs have enhanced AI capabilities, but also increased the risk posed by malicious requests, highlighting the need for effective LLM safeguards to detect such queries. Existing approaches largely rely on classifier-based…

As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that…

As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified. Numerous guardrail models and benchmarks have been developed to ensure LLM content safety. However, existing…

Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous due to subtle environmental states. Existing safeguards…