Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm categories, we introduce DynaGuard, a suite of dynamic guardian models offering novel flexibility by evaluating text based on user-defined policies, and DynaBench, a dataset for training and evaluating dynamic guardian models. Our models provide both rapid detection of policy violations and a chain-of-thought reasoning option that articulate and justify model outputs. Critically, DynaGuard not only surpasses static models in detection accuracy on traditional safety categories, but is competitive with frontier reasoning models on free-form policy violations, all in a fraction of the time. This makes DynaGuard an critical tool for language model guardrails.
@article{arxiv.2509.02563,
title = {DynaGuard: A Dynamic Guardian Model With User-Defined Policies},
author = {Monte Hoover and Vatsal Baherwani and Neel Jain and Khalid Saifullah and Joseph Vincent and Chirag Jain and Melissa Kazemi Rad and C. Bayan Bruss and Ashwinee Panda and Tom Goldstein},
journal= {arXiv preprint arXiv:2509.02563},
year = {2025}
}