Inan and colleagues: taxonomy-conditioned Llama Guard moderation

What changed

Trained a language-model classifier to label user prompts and assistant responses against a configurable safety taxonomy, providing an input/output safeguard with text explanations and task-specific adaptation.

Scientific scope

Trained a language-model classifier to label user prompts and assistant responses against a configurable safety taxonomy, providing an input/output safeguard with text explanations and task-specific adaptation. Prompt risk and response risk are separate classification tasks. Performance depends on taxonomy, training examples and deployment distribution; a classifier label is not a guarantee that all harmful content is blocked or benign content retained.

Evidence

The linked original works support the scoped statement and contribution attribution. WRS has not independently replayed experiments or reconstructed a full mathematical proof. Prompt risk and response risk are separate classification tasks. Performance depends on taxonomy, training examples and deployment distribution; a classifier label is not a guarantee that all harmful content is blocked or benign content retained.

Contributors

• The named authors in the research record · SCIENCE: Source-listed authors for the exact contribution; experimental subjects are not autonomous scientific authors. Source support and predecessor work retain separate roles. Individual effort shares and unresolved identities are not inferred.

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

Provisional WRS assessment, edition 2026-10-23.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction