Key points are not available for this paper at this time.
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.
Building similarity graph...
Analyzing shared references across papers
Loading...
Ohjoon Kwon
Donghyeon Jeon
Nayoung Choi
Building similarity graph...
Analyzing shared references across papers
Loading...
Kwon et al. (Thu,) studied this question.
www.synapsesocial.com/papers/68e67aa1b6db643587604f0a — DOI: https://doi.org/10.48550/arxiv.2405.19795
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: