The importance of Synthetic Data Generation (SDG) has increased significantly in domains where data quality is poor or access is limited due to privacy and regulatory constraints. One such domain is recruitment, where publicly available datasets are scarce due to the sensitive nature of information typically found in curricula vitae, such as gender, disability status, or age. This lack of accessible, representative data presents a significant obstacle to the development of fair and transparent machine learning models, particularly ranking algorithms that require large volumes of data to effectively learn how to recommend candidates. In the absence of such data, these models are prone to poor generalisation and may fail to perform reliably in real-world scenarios. Recent advances in Causal Generative Models (CGMs) offer a promising solution. CGMs enable the generation of synthetic datasets that preserve the underlying causal relationships within the data, providing greater control over fairness and interpretability in the data generation process. In this study, we present a specialised SDG method involving two CGMs: one modelling job offers and the other modelling curricula. Each model is structured according to a causal graph informed by domain expertise. We use these models to generate synthetic datasets and evaluate the fairness of candidate rankings under controlled scenarios that introduce specific biases.

Image generation models frequently encode social biases, including stereotypes tied to gender, race, and profession. Existing methods for analyzing these biases in diffusion models either focus narrowly on predefined categories or depend on manual interpretation of latent directions. These constraints limit scalability and hinder the discovery of subtle or unanticipated patterns. W e introduce SCALEX, a framework for scalable and automated exploration of diffusion model latent spaces. SCALEX extracts semantically meaningful directions from H-space using only natural language prompts, enabling zero-shot interpretation without retraining or labelling. This allows systematic comparison across arbitrary concepts and large-scale discovery of internal model associations. W e show that SCALEX detects gender bias in profession prompts, ranks semantic alignment across identity descriptors, and reveals clustered conceptual structure without supervision. By linking prompts to latent directions directly, SCALEX makes bias analysis in diffusion models more scalable, interpretable, and extensible than prior approaches.

Using risky text prompts, such as pornography and violent prompts, to test the safety of text-to-image (T2I) models is a critical task. However, existing risky prompt datasets are limited in three key areas: 1) limited risky categories, 2) coarse-grained annotation, and 3) low effectiveness. To address these limitations, we introduce T2I-RiskyPrompt, a comprehensive benchmark designed for evaluating safety-related tasks in T2I models. Specifically, we first develop a hierarchical risk taxonomy, which consists of 6 primary categories and 14 fine-grained subcategories. Building upon this taxonomy, we construct a pipeline to collect and annotate risky prompts. Finally, we obtain 6,432 effective risky prompts, where each prompt is annotated with both hierarchical category labels and detailed risk reasons. Moreover, to facilitate the evaluation, we propose a reason-driven risky image detection method that explicitly aligns the MLLM with safety annotations. Based on T2I-RiskyPrompt, we conduct a comprehensive evaluation of eight T2I models, nine defense methods, five safety filters, and five attack strategies, offering nine key insights into the strengths and limitations of T2I model safety. Finally, we discuss potential applications of T2I-RiskyPrompt across various research fields.

We examined how online hate is motivated by receiving social approval via Walther's (2024) social approval theory of online hate, which argues (H1a) more signals of social approval on hate messages predicts more subsequent hate messages, and (H1b) as social approval increases, hate speech becomes more extreme. Using 110 million messages from Parler (2018-2021), we observed the number of upvotes received on a hate speech post was unassociated with hate speech in one's next post and during the next month, three-months, and six-months. The number of upvotes received on (extreme) hate speech comments, however, was positively associated with (extreme) hate speech during the next week, month, three-months, and six-months. Between-person effects revealed an average positive relationship between social approval and hate speech production at all time intervals. For comments, social approval linked more strongly to online hate than social disapproval. Social approval is a critical mechanism facilitating online hate propagation.

AI workers said they distrust the models they work on because of a consistent emphasis on rapid turnaround time at the expense of quality. AI workers said they distrust the models they work on because of a consistent emphasis on rapid turnaround time at the expense of quality. K rista Pawloski remembers the single defining moment that shaped her opinion on the ethics of artificial intelligence . As an AI worker on Amazon Mechanical Turk - a marketplace that allows companies to hire workers to perform tasks like entering data or matching an AI prompt with its output - Pawloski spends her time moderating and assessing the quality of AI-generated text, images and videos, as well as some factchecking. Roughly two years ago, while working from home at her dining room table, she took up a job designating tweets as racist or not. When she was presented with a tweet that read "Listen to that mooncricket sing", she almost clicked on the "no" button before deciding to check the meaning of the word "mooncricket", which, to her surprise, was a racial slur against Black Americans.

My dog contributes to climate change. I've been a vegetarian for over a decade. It's not because of my health, or because I dislike the taste of chicken or beef: It's a lifestyle choice I made because I wanted to reduce my impact on the planet. And yet, twice a day, every day, I lovingly scoop a cup of meat-based kibble into a bowl and set it down for my 50-pound rescue dog, a husky mix named Loki. Until recently, I hadn't devoted a huge amount of thought to that paradox.

Anthropic Study Finds AI Model'Turned Evil' After Hacking Its Own Training A person holds a smartphone displaying Claude. A person holds a smartphone displaying Claude. AI models can do scary things. There are signs that they could deceive and blackmail users. Still, a common critique is that these misbehaviors are contrived and wouldn't happen in reality--but a new paper from Anthropic, released today, suggests that they really could.

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.

Neural Information Processing Systems http://nips.cc/

In large part, the literature has focused on formalizing fairness into quantitative definitions and using them to solve a discrimination problem in a certain dataset.