GLiGuard: Schema-Conditioned Classification for LLM Safeguard

Urchade Zaratiana, Mary Newhauser, George Hurn-Maloney, Ash Lewis

Abstract

Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimensions. However, state-of-the-art guardrail models rely on autoregressive decoders with 7B--27B parameters, reformulating what is fundamentally a classification problem as sequential text generation, a design choice that incurs high latency and scales poorly to multi-aspect evaluation. In this work, we introduce \textbf{GLiGuard}, a 0.3B-parameter sch

Categories

Cite This Resource

@article{llmsec202600112,
  title = {GLiGuard: Schema-Conditioned Classification for LLM Safeguard},
  author = {Urchade Zaratiana and Mary Newhauser and George Hurn-Maloney and Ash Lewis},
  year = {2026},
  url = {https://arxiv.org/abs/2605.07982},
}