English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce Llama Guard, an LLM-based input-output safeguard model gearedtowards Human-AI conversation use cases. Our model incorporates a safety risktaxonomy, a valuable tool for categorizing a specific set of safety risks foundin LLM prompts (i.e., prompt classification). This taxonomy is alsoinstrumental in classifying the responses generated by LLMs to these prompts, aprocess we refer to as response classification. For the purpose of both promptand response classification, we have meticulously gathered a dataset of highquality. Llama Guard, a Llama2-7b model that is instruction-tuned on ourcollected dataset, albeit low in volume, demonstrates strong performance onexisting benchmarks such as the OpenAI Moderation Evaluation dataset andToxicChat, where its performance matches or exceeds that of currently availablecontent moderation tools. Llama Guard functions as a language model, carryingout multi-class classification and generating binary decision scores.Furthermore, the instruction fine-tuning of Llama Guard allows for thecustomization of tasks and the adaptation of output formats. This featureenhances the model's capabilities, such as enabling the adjustment of taxonomycategories to align with specific use cases, and facilitating zero-shot orfew-shot prompting with diverse taxonomies at the input. We are making LlamaGuard model weights available and we encourage researchers to further developand adapt them to meet the evolving needs of the community for AI safety.

Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations