AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
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_ | 1866917489240178688 |
|---|---|
| author | Chen, Chen Gong, Xueluan Liu, Ziyao Jiang, Weifeng Goh, Si Qi Lam, Kwok-Yan |
| author_facet | Chen, Chen Gong, Xueluan Liu, Ziyao Jiang, Weifeng Goh, Si Qi Lam, Kwok-Yan |
| contents | AI Safety is an emerging area of critical importance to the safe adoption and deployment of AI systems. With the rapid proliferation of AI and especially with the recent advancement of Generative AI (or GAI), the technology ecosystem behind the design, development, adoption, and deployment of AI systems has drastically changed, broadening the scope of AI Safety to address impacts on public safety and national security. In this paper, we propose a novel architectural framework for understanding and analyzing AI Safety; defining its characteristics from three perspectives: Trustworthy AI, Responsible AI, and Safe AI. We provide an extensive review of current research and advancements in AI safety from these perspectives, highlighting their key challenges and mitigation approaches. Through examples from state-of-the-art technologies, particularly Large Language Models (LLMs), we present innovative mechanism, methodologies, and techniques for designing and testing AI safety. Our goal is to promote advancement in AI safety research, and ultimately enhance people's trust in digital transformation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12935 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions Chen, Chen Gong, Xueluan Liu, Ziyao Jiang, Weifeng Goh, Si Qi Lam, Kwok-Yan Artificial Intelligence AI Safety is an emerging area of critical importance to the safe adoption and deployment of AI systems. With the rapid proliferation of AI and especially with the recent advancement of Generative AI (or GAI), the technology ecosystem behind the design, development, adoption, and deployment of AI systems has drastically changed, broadening the scope of AI Safety to address impacts on public safety and national security. In this paper, we propose a novel architectural framework for understanding and analyzing AI Safety; defining its characteristics from three perspectives: Trustworthy AI, Responsible AI, and Safe AI. We provide an extensive review of current research and advancements in AI safety from these perspectives, highlighting their key challenges and mitigation approaches. Through examples from state-of-the-art technologies, particularly Large Language Models (LLMs), we present innovative mechanism, methodologies, and techniques for designing and testing AI safety. Our goal is to promote advancement in AI safety research, and ultimately enhance people's trust in digital transformation. |
| title | AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2408.12935 |