A Survey on Responsible Generative AI: What to Generate and What Not
It provides a unified perspective on safety issues for building responsible generative AI across domains like healthcare and education, but is a survey paper rather than presenting new research.
This paper investigates practical requirements for responsible generative AI, outlining five key considerations including generating truthful content and avoiding toxic content, and reviews recent advancements and challenges in addressing these requirements across textual and visual models.
In recent years, generative AI (GenAI), like large language models and text-to-image models, has received significant attention across various domains. However, ensuring the responsible generation of content by these models is crucial for their real-world applicability. This raises an interesting question: What should responsible GenAI generate, and what should it not? To answer the question, this paper investigates the practical responsible requirements of both textual and visual generative models, outlining five key considerations: generating truthful content, avoiding toxic content, refusing harmful instruction, leaking no training data-related content, and ensuring generated content identifiable. Specifically, we review recent advancements and challenges in addressing these requirements. Besides, we discuss and emphasize the importance of responsible GenAI across healthcare, education, finance, and artificial general intelligence domains. Through a unified perspective on both textual and visual generative models, this paper aims to provide insights into practical safety-related issues and further benefit the community in building responsible GenAI.