相关论文: Safety and Fairness for Content Moderation in Gene…

The Generative AI Ethics Playbook provides guidance for identifying and mitigating risks of machine learning systems across various domains, including natural language processing, computer vision, and generative AI. This playbook aims to…

Fairness is a crucial concern for generative models, which not only reflect but can also amplify societal and cultural biases. Existing fairness notions for generative models are largely adapted from classification and focus on balancing…

AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content…

Watermarking embeds information into digital content like images, audio, or text, imperceptible to humans but robustly detectable by specific algorithms. This technology has important applications in many challenges of the industry such as…

Generative AI enables automated, effective manipulation at scale. Despite the growing general ethical discussion around generative AI, the specific manipulation risks remain inadequately investigated. This article outlines essential…

Generative AI systems powered by Large Language Models (LLMs) usually use content moderation to prevent harmful content spread. To evaluate the robustness of content moderation, several metamorphic testing techniques have been proposed to…

To responsibly develop Generative AI (GenAI) products, it is critical to define the scope of acceptable inputs and outputs. What constitutes a "safe" response is an actively debated question. Academic work puts an outsized focus on…

Generative AI models like GPT-4o and DALL-E 3 are reshaping digital content creation, offering industries tools to generate diverse and sophisticated text and images with remarkable creativity and efficiency. This paper examines both the…

Content moderation plays a critical role in shaping safe and inclusive online environments, balancing platform standards, user expectations, and regulatory frameworks. Traditionally, this process involves operationalising policies into…

Automated content moderation has long been used to help identify and filter undesired user-generated content online. But such systems have a history of incorrectly flagging content by and about marginalized identities for removal.…

Designing sustainable systems involves complex interactions between environmental resources, social impacts, and economic issues. In a constrained world, the challenge is to achieve a balanced design across those dimensions while avoiding…

As large language models become integral to high-stakes applications, ensuring their robustness and fairness is critical. Despite their success, large language models remain vulnerable to adversarial attacks, where small perturbations, such…

Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models are developed, to protect users' rights and safety, most of…

As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to undertake a holistic evaluation and refinement of associated…

Generative AI, in particular text-based "foundation models" (large models trained on a huge variety of information including the internet), can generate speech that could be problematic under a wide range of liability regimes. Machine…

Generative AI has made significant strides, yet concerns about the accuracy and reliability of its outputs continue to grow. Such inaccuracies can have serious consequences such as inaccurate decision-making, the spread of false…

The significant advancements in applying Artificial Intelligence (AI) to healthcare decision-making, medical diagnosis, and other domains have simultaneously raised concerns about the fairness and bias of AI systems. This is particularly…

Disparities in the societal harms and impacts of Generative AI (GenAI) systems highlight the critical need for effective unfairness measurement approaches. While numerous benchmarks exist, designing valid measurements requires proper…

Recent advances in the capacity of large language models to generate human-like text have resulted in their increased adoption in user-facing settings. In parallel, these improvements have prompted a heated discourse around the risks of…

Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit…