SLM as Guardian: Pioneering AI Safety with Small Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916578475376640 |
|---|---|
| author | Kwon, Ohjoon Jeon, Donghyeon Choi, Nayoung Cho, Gyu-Hwung Kim, Changbong Lee, Hyunwoo Kang, Inho Kim, Sun Park, Taiwoo |
| author_facet | Kwon, Ohjoon Jeon, Donghyeon Choi, Nayoung Cho, Gyu-Hwung Kim, Changbong Lee, Hyunwoo Kang, Inho Kim, Sun Park, Taiwoo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19795 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SLM as Guardian: Pioneering AI Safety with Small Language Models Kwon, Ohjoon Jeon, Donghyeon Choi, Nayoung Cho, Gyu-Hwung Kim, Changbong Lee, Hyunwoo Kang, Inho Kim, Sun Park, Taiwoo Computation and Language Artificial Intelligence 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. |
| title | SLM as Guardian: Pioneering AI Safety with Small Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.19795 |