一作ACL 2026Poster· Natural Language Processing
Domain Generalizable AI Guardrails with Augmented Policy Training
Minqian Liu · Ioana Baldini · David Rabinowitz · David S Rosenberg · Sebastian Gehrmann · Mark Dredze
摘要
AI guardrail systems support usage policies by determining whether a user query or a generated response is allowed or forbidden under the policy. Fine-tuned guardrails – such as LlamaGuard and ShieldGemma – include policy definitions in prompts during training that can be updated during inference...