We introduce Llama Guard, an LLM-based input-output safeguard model geared towards
Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a …

Recently, social media platforms are heavily moderated to prevent the spread of online hate
speech, which is usually fertile in toxic words and is directed toward an individual or a …

Dialogue models trained on human conversations inadvertently learn to generate toxic
responses. In addition to producing explicitly offensive utterances, these models can also …

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 …

Social media platforms were conceived to act as online town squares' where people could
get together, share information and communicate with each other peacefully. However …

Annotators are not fungible. Their demographics, life experiences, and backgrounds all
contribute to how they label data. However, NLP has only recently considered how …

Machine learning (ML) datasets, often perceived as neutral, inherently encapsulate abstract
and disputed social constructs. Dataset curators frequently employ value-laden terms such …

The user-generated content on the internet including that on social media may contain
offensive language and hate speech which negatively affect the mental health of the whole …

Language serves as a powerful tool for the manifestation of societal belief systems. In doing
so, it also perpetuates the prevalent biases in our society. Gender bias is one of the most …

Machine learning (ML)-based content moderation tools are essential to keep online spaces
free from hateful communication. Yet ML tools can only be as capable as the quality of the …