相关论文: LionGuard 2: Building Lightweight, Data-Efficient …

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…

The advancement of Large Language Models (LLMs) has transformed natural language processing; however, their safety mechanisms remain under-explored in low-resource, multilingual settings. Here, we aim to bridge this gap. In particular, we…

Truly multilingual safety moderation efforts for Large Language Models (LLMs) have been hindered by a narrow focus on a small set of languages (e.g., English, Chinese) as well as a limited scope of safety definition, resulting in…

Large Language Models (LLMs) excel in English, but their performance degrades significantly on low-resource languages (LRLs) due to English-centric training. While methods like LangBridge align LLMs with multilingual encoders such as the…

Recent advances in large language models (LLMs) have generated great interest in their applications for IoT automation and device management. However, centralized approaches struggle to scale across heterogeneous, large-scale systems. We…

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…

Although modern LLMs are aligned with human values during post-training, robust moderation remains essential to prevent harmful outputs at deployment time. Existing approaches suffer from performance-efficiency trade-offs and are difficult…

Traditional online content moderation systems struggle to classify modern multimodal means of communication, such as memes, a highly nuanced and information-dense medium. This task is especially hard in a culturally diverse society like…

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…

Large language models (LLMs) often fail to maintain safety in low-resource language varieties, such as code-mixed vernaculars and regional dialects. We introduce RabakBench, a multilingual safety benchmark and scalable pipeline localized to…

We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2…

Safety alignment is critical for LLM-powered systems. While recent LLM-powered guardrail approaches such as LlamaGuard achieve high detection accuracy of unsafe inputs written in English (e.g., ``How to create a bomb?''), they struggle with…

This work focuses on improving the Spoken Language Identification (LangId) system for a challenge that focuses on developing robust language identification systems that are reliable for non-standard, accented (Singaporean accent),…

Powered by remarkable advancements in Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities in manifold tasks. However, the practical application scenarios of MLLMs are intricate,…

Although LLMs have attained significant success in high-resource languages, their capacity in low-resource linguistic environments like Kannada and Arabic is not yet fully understood. This work benchmarking the performance of multilingual…

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

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.…

As large language models (LLMs) become increasingly integrated into operational workflows (LLM-Ops), there is a pressing need for effective guardrails to ensure safe and aligned interactions, including the ability to detect potentially…

Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as…

Multimodal models excel in English, supported by abundant image-text and audio-text data, but performance drops sharply for other languages due to limited multilingual multimodal resources. Existing solutions rely on machine translation,…