Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as mobile phones, more and more of which are running LLM-based applications locally. We introduce LoRA-Guard, a parameter-efficient guardrail adaptation method that relies on knowledge sharing between LLMs and guardrail models. LoRA-Guard extracts language features from the LLMs and adapts them for the content moderation task using low-rank adapters, while a dual-path design prevents any performance degradation on the generative task. We show that LoRA-Guard outperforms existing approaches with 100-1000x lower parameter overhead while maintaining accuracy, enabling on-device content moderation.
@article{arxiv.2407.02987,
title = {LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models},
author = {Hayder Elesedy and Pedro M. Esperança and Silviu Vlad Oprea and Mete Ozay},
journal= {arXiv preprint arXiv:2407.02987},
year = {2024}
}