SLM as Guardian: Pioneering AI Safety with Small Language Models

TL;DR

This paper introduces a modular safety system using small language models to detect harmful queries and generate safeguards, reducing costs and maintaining helpfulness compared to larger models.

Contribution

It proposes a multi-task learning approach that combines harmful query detection and safeguard response generation within a small language model.

Findings

Achieves comparable or better safety performance than larger models

Reduces training costs and complexity

Maintains helpfulness while enhancing safety

Abstract

Most prior safety research of large language models (LLMs) has focused on enhancing the alignment of LLMs to better suit the safety requirements of humans. However, internalizing such safeguard features into larger models brought challenges of higher training cost and unintended degradation of helpfulness. To overcome such challenges, a modular approach employing a smaller LLM to detect harmful user queries is regarded as a convenient solution in designing LLM-based system with safety requirements. In this paper, we leverage a smaller LLM for both harmful query detection and safeguard response generation. We introduce our safety requirements and the taxonomy of harmfulness categories, and then propose a multi-task learning mechanism fusing the two tasks into a single model. We demonstrate the effectiveness of our approach, providing on par or surpassing harmful query detection and safeguard response performance compared to the publicly available LLMs.