Large Language Models (LLMs) have unlocked new capabilities and applications; however,
evaluating the alignment with human preferences still poses significant challenges. To …

With the significant development of large models in recent years, Large Vision-Language
Models (LVLMs) have demonstrated remarkable capabilities across a wide range of …

This paper introduces v0. 5 of the AI Safety Benchmark, which has been created by the
MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to …

Evaluating aligned large language models'(LLMs) ability to recognize and reject unsafe user
requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts …

In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety
measures is paramount. To meet this crucial need, we propose\emph {SALAD-Bench}, a …

We introduce WildGuard--an open, light-weight moderation tool for LLM safety that achieves
three goals:(1) identifying malicious intent in user prompts,(2) detecting safety risks of model …

Accurate and consistent evaluation is crucial for decision-making across numerous fields,
yet it remains a challenging task due to inherent subjectivity, variability, and scale. Large …

We present ShieldGemma, a comprehensive suite of LLM-based safety content moderation
models built upon Gemma2. These models provide robust, state-of-the-art predictions of …

Large language models (LLMs) have exhibited great potential in autonomously completing
tasks across real-world applications. Despite this, these LLM agents introduce unexpected …

Recent advancements in Large Language Models (LLMs) have showcased remarkable
capabilities across various tasks in different domains. However, the emergence of biases …