It is good news for anyone who likes to sunbathe close to home. Bosses at the Met Office say weather forecasts could soon become'hyper local' - even predicting the temperature in your back garden. By using artificial intelligence and data collected by amateur forecasters, the new model was able to predict precisely how hot it will get down to the level of an individual street. The Met Office's standard forecasting model divides the UK into grid squares of 1.5km. By using AI techniques, the new method is able to predict the weather within 100 metre squares'showing the potential for hyper-local forecasts for temperature, even within the same street,' the Met Office said.

Statistical agencies rely on sampling techniques to collect socio-demographic data crucial for policy-making and resource allocation. This paper shows that surveys of important societal relevance introduce sampling errors that unevenly impact group-level estimates, thereby compromising fairness in downstream decisions. To address these issues, this paper introduces an optimization approach modeled on real-world survey design processes, ensuring sampling costs are optimized while maintaining error margins within prescribed tolerances. Additionally, privacy-preserving methods used to determine sampling rates can further impact these fairness issues. The paper explores the impact of differential privacy on the statistics informing the sampling process, revealing a surprising effect: not only the expected negative effect from the addition of noise for differential privacy is negligible, but also this privacy noise can in fact reduce unfairness as it positively biases smaller counts. These findings are validated over an extensive analysis using datasets commonly applied in census statistics.

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have the potential to cause real-world impact. Policymakers, model providers, and other researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 distinct CTF competitions, chosen to be recent, meaningful, and spanning a wide range of difficulties. Each task includes its own description, starter files, and is initialized in an environment where an agent can execute bash commands and observe outputs. Since many tasks are beyond the capabilities of existing LM agents, we introduce subtasks, which break down a task into intermediary steps for more gradated evaluation; we add subtasks for 17 of the 40 tasks. To evaluate agent capabilities, we construct a cybersecurity agent and evaluate 7 models: GPT-4o, Claude 3 Opus, Claude 3.5 Sonnet, Mixtral 8x22b Instruct, Gemini 1.5 Pro, Llama 3 70B Chat, and Llama 3.1 405B Instruct. Without guidance, we find that agents are able to solve only the easiest complete tasks that took human teams up to 11 minutes to solve, with Claude 3.5 Sonnet and GPT-4o having the highest success rates. Finally, subtasks provide more signal for measuring performance compared to unguided runs, with models achieving a 3.2\% higher success rate on complete tasks with subtask-guidance than without subtask-guidance. All code and data are publicly available at https://cybench.github.io

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

We present GERestaurant, a novel dataset consisting of 3,078 German language restaurant reviews manually annotated for Aspect-Based Sentiment Analysis (ABSA). All reviews were collected from Tripadvisor, covering a diverse selection of restaurants, including regional and international cuisine with various culinary styles. The annotations encompass both implicit and explicit aspects, including all aspect terms, their corresponding aspect categories, and the sentiments expressed towards them. Furthermore, we provide baseline scores for the four ABSA tasks Aspect Category Detection, Aspect Category Sentiment Analysis, End-to-End ABSA and Target Aspect Sentiment Detection as a reference point for future advances. The dataset fills a gap in German language resources and facilitates exploration of ABSA in the restaurant domain.

Foundation models have triggered a paradigm shift in computer vision and are increasingly being adopted in remote sensing, particularly for multispectral imagery. Yet, their potential in hyperspectral imaging (HSI) remains untapped due to the absence of comprehensive and globally representative hyperspectral datasets. To close this gap, we introduce SpectralEarth, a large-scale multi-temporal dataset designed to pretrain hyperspectral foundation models leveraging data from the Environmental Mapping and Analysis Program (EnMAP). SpectralEarth comprises 538,974 image patches covering 415,153 unique locations from more than 11,636 globally distributed EnMAP scenes spanning two years of archive. Additionally, 17.5% of these locations include multiple timestamps, enabling multi-temporal HSI analysis. Utilizing state-of-the-art self-supervised learning (SSL) algorithms, we pretrain a series of foundation models on SpectralEarth. We integrate a spectral adapter into classical vision backbones to accommodate the unique characteristics of HSI. In tandem, we construct four downstream datasets for land-cover and crop-type mapping, providing benchmarks for model evaluation. Experimental results support the versatility of our models, showcasing their generalizability across different tasks and sensors. We also highlight computational efficiency during model fine-tuning. The dataset, models, and source code will be made publicly available.

Human feedback is essential for building human-centered AI systems across domains where disagreement is prevalent, such as AI safety, content moderation, or sentiment analysis. Many disagreements, particularly in politically charged settings, arise because raters have opposing values or beliefs. Vicarious annotation is a method for breaking down disagreement by asking raters how they think others would annotate the data. In this paper, we explore the use of vicarious annotation with analytical methods for moderating rater disagreement. We employ rater cohesion metrics to study the potential influence of political affiliations and demographic backgrounds on raters' perceptions of offense. Additionally, we utilize CrowdTruth's rater quality metrics, which consider the demographics of the raters, to score the raters and their annotations. We study how the rater quality metrics influence the in-group and cross-group rater cohesion across the personal and vicarious levels.

Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link prediction yet suggest conflicting predictions for certain queries, termed \textit{predictive multiplicity} in literature. This behavior poses substantial risks for KGE-based applications in high-stake domains but has been overlooked in KGE research. In this paper, we define predictive multiplicity in link prediction. We introduce evaluation metrics and measure predictive multiplicity for representative KGE methods on commonly used benchmark datasets. Our empirical study reveals significant predictive multiplicity in link prediction, with $8\%$ to $39\%$ testing queries exhibiting conflicting predictions. To address this issue, we propose leveraging voting methods from social choice theory, significantly mitigating conflicts by $66\%$ to $78\%$ according to our experiments.

As Boyd explained at a conference in June, the key question for OBIM is, "If we pick up someone from Panama at the southern border at age four, say, and then pick them up at age six, are we going to recognize them?" Facial recognition technology (FRT) has traditionally not been applied to children, largely because training data sets of real children's faces are few and far between, and consist of either low-quality images drawn from the internet or small sample sizes with little diversity. Such limitations reflect the significant sensitivities regarding privacy and consent when it comes to minors. According to Syracuse University's Transactional Records Access Clearinghouse (TRAC), 339,234 children arrived at the US-Mexico border in 2022, the last year for which numbers are currently available. Of those children, 150,000 were unaccompanied--the highest annual number on record.

We introduce Synthetic Alignment data Generation for Safety Evaluation and Red Teaming (SAGE-RT or SAGE) a novel pipeline for generating synthetic alignment and red-teaming data. Existing methods fall short in creating nuanced and diverse datasets, providing necessary control over the data generation and validation processes, or require large amount of manually generated seed data. SAGE addresses these limitations by using a detailed taxonomy to produce safety-alignment and red-teaming data across a wide range of topics. We generated 51,000 diverse and in-depth prompt-response pairs, encompassing over 1,500 topics of harmfulness and covering variations of the most frequent types of jailbreaking prompts faced by large language models (LLMs). We show that the red-teaming data generated through SAGE jailbreaks state-of-the-art LLMs in more than 27 out of 32 sub-categories, and in more than 58 out of 279 leaf-categories (sub-sub categories). The attack success rate for GPT-4o, GPT-3.5-turbo is 100% over the sub-categories of harmfulness. Our approach avoids the pitfalls of synthetic safety-training data generation such as mode collapse and lack of nuance in the generation pipeline by ensuring a detailed coverage of harmful topics using iterative expansion of the topics and conditioning the outputs on the generated raw-text. This method can be used to generate red-teaming and alignment data for LLM Safety completely synthetically to make LLMs safer or for red-teaming the models over a diverse range of topics.