AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions

TL;DR

This paper presents a comprehensive framework and review of AI safety, focusing on large language models, highlighting challenges, mitigation strategies, and future research directions to ensure safe AI deployment.

Contribution

It introduces a novel architectural framework for AI safety, categorizing it into Trustworthy, Responsible, and Safe AI, and reviews state-of-the-art safety techniques for large language models.

Findings

Identifies key challenges in AI safety for LLMs

Reviews current mitigation approaches and methodologies

Proposes future directions for AI safety research

Abstract

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.