We introduce {\bf Swan}, a family of embedding models centred around the Arabic language, addressing both small-scale and large-scale use cases. Swan includes two variants: Swan-Small, based on ARBERTv2, and Swan-Large, built on ArMistral, a pretrained Arabic large language model. To evaluate these models, we propose ArabicMTEB, a comprehensive benchmark suite that assesses cross-lingual, multi-dialectal, multi-domain, and multi-cultural Arabic text embedding performance, covering eight diverse tasks and spanning 94 datasets. Swan-Large achieves state-of-the-art results, outperforming Multilingual-E5-large in most Arabic tasks, while the Swan-Small consistently surpasses Multilingual-E5-base. Our extensive evaluations demonstrate that Swan models are both dialectally and culturally aware, excelling across various Arabic domains while offering significant monetary efficiency. This work significantly advances the field of Arabic language modelling and provides valuable resources for future research and applications in Arabic natural language processing. Our models and benchmark will be made publicly accessible for research.

AI systems increasingly shape critical decisions across personal and societal domains. While empirical risk minimization (ERM) drives much of the AI success, it typically prioritizes accuracy over trustworthiness, often resulting in biases, opacity, and other adverse effects. This paper discusses how key requirements for trustworthy AI can be translated into design choices for the components of ERM. We hope to provide actionable guidance for building AI systems that meet emerging standards for trustworthiness of AI.

AfriClimate AI is a grassroots community focused on leveraging artificial intelligence to tackle climate challenges in Africa. We spoke to Amal Nammouchi, one of the co-founders of AfriClimate AI, about the inspiration behind the initiative, some of their activities and projects, and plans for the future. Everything started last year at the Deep Learning Indaba in Ghana. The Deep Learning Indaba is the largest African AI community gathering and it happens once a year. The spark for AfriClimate AI came from a workshop with the work of one of our co-founders Rendani Mbuvha.

Generative Artificial Intelligence (AI) technologies are in a phase of unprecedented rapid development following the landmark release of Chat-GPT, which brought the phenomenon to wide public attention. As the deployment of AI products rises geometrically, considerable attention is being given to the threats and opportunities that AI technologies offer, and to the need for regulatory and standards initiatives to ensure that use of the technology aligns with societal needs and generates broad benefits while mitigating risks and threats. This manuscript is the third of a series of White Papers informing the development of IEEE-SA's p3995 {\it `Standard for the Implementation of Safeguards, Controls, and Preventive Techniques for Artificial Intelligence Models'} \cite{P3395}, Chair Marina Cort\^{e}s. This part focuses on assessing calmly and objectively, as far as is possible, the current state of Artificial Intelligence (AI) technology development and identifying predominant trends, prospects, and ensuing risks. It necessarily forms a snapshot of the current instant of a rapidly-evolving landscape, with new products and innovations emerging continuously. While our main focus is on software and hardware developments and their corporate context, we also briefly review progress on robotics within the AI context and describe some implications of the substantial and growing AI energy demand.

Worst-case fairness with off-the-shelf demographics achieves group parity by maximizing the model utility of the worst-off group. Nevertheless, demographic information is often unavailable in practical scenarios, which impedes the use of such a direct max-min formulation. Recent advances have reframed this learning problem by introducing the lower bound of minimal partition ratio, denoted as $\alpha$, as side information, referred to as ``$\alpha$-sized worst-case fairness'' in this paper. We first justify the practical significance of this setting by presenting noteworthy evidence from the data privacy perspective, which has been overlooked by existing research. Without imposing specific requirements on loss functions, we propose reweighting the training samples based on their intrinsic importance to fairness. Given the global nature of the worst-case formulation, we further develop a stochastic learning scheme to simplify the training process without compromising model performance. Additionally, we address the issue of outliers and provide a robust variant to handle potential outliers during model training. Our theoretical analysis and experimental observations reveal the connections between the proposed approaches and existing ``fairness-through-reweighting'' studies, with extensive experimental results on fairness benchmarks demonstrating the superiority of our methods.

We study the analysis of all the movements of the population on the basis of their mobility from one node to another, to observe, measure, and predict the impact of traffic according to this mobility. The frequency of congestion on roads directly or indirectly impacts our economic or social welfare. Our work focuses on exploring some machine learning methods to predict (with a certain probability) traffic in a multimodal transportation network from population mobility data. We analyze the observation of the influence of people's movements on the transportation network and make a likely prediction of congestion on the network based on this observation (historical basis).

Natural Language Interfaces for Databases empower non-technical users to interact with data using natural language (NL). Advanced approaches, utilizing either neural sequence-to-sequence or more recent sophisticated large-scale language models, typically implement NL to SQL (NL2SQL) translation in an end-to-end fashion. However, like humans, these end-to-end translation models may not always generate the best SQL output on their first try. In this paper, we propose CycleSQL, an iterative framework designed for end-to-end translation models to autonomously generate the best output through self-evaluation. The main idea of CycleSQL is to introduce data-grounded NL explanations of query results as self-provided feedback, and use the feedback to validate the correctness of the translation iteratively, hence improving the overall translation accuracy. Extensive experiments, including quantitative and qualitative evaluations, are conducted to study CycleSQL by applying it to seven existing translation models on five widely used benchmarks. The results show that 1) the feedback loop introduced in CycleSQL can consistently improve the performance of existing models, and in particular, by applying CycleSQL to RESDSQL, obtains a translation accuracy of 82.0% (+2.6%) on the validation set, and 81.6% (+3.2%) on the test set of Spider benchmark; 2) the generated NL explanations can also provide insightful information for users, aiding in the comprehension of translation results and consequently enhancing the interpretability of NL2SQL translation.

This article presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services.

T erry Y ue Zhuo Massimo Caccia Monash University ServiceNow Research Sea AI Lab A BSTRACT The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent version updates while maintaining compatibility with previous versions. Existing code completion benchmarks often overlook this dynamic aspect, and the one that does consider it relies on static code prediction tasks without execution-based evaluation, offering a limited perspective on a model's practical usability. To address this gap, we introduce GitChameleon, a novel, manually curated dataset comprising 116 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. GitChameleon is designed to rigorously assess the ability of modern large language models (LLMs) to generate version-specific code that is not only syntactically correct but also functionally accurate upon execution. Our comprehensive evaluations reveal that state-of-the-art LLMs struggle with this task; for instance, GPT -4oachieves a pass@10 of only 39.9% (43.7% when provided with error feedback), highlighting the complexity of the problem and the limitations of current models. By providing an execution-based benchmark that emphasizes the dynamic nature of code libraries, GitChameleon serves as a critical tool to advance the development of more adaptable and reliable code generation models. Code, being a dynamic and constantly evolving environment, necessitates a continuous process of adaptation to stay in sync with the rapidly shifting paradigms, frameworks, and methodologies within the software development domain. The inherent variability in coding styles, the emergence of new programming languages, and the continuous evolution of libraries and packages underscore the imperative for an active approach in updating code generation models. In response to the needs of practical coding environments, several large language models (LLMs) have been introduced, including StarCoder (Li et al., 2023), DeepSeek-Coder (Guo et al., 2024), CodeLlama (Rozi ` ere et al., 2023), among others.

A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value predictions. However, dopamine is synchronously distributed in regionally homogeneous concentrations, which does not support explicit credit assignment (like used by backpropagation). It is unclear whether distributed errors alone are sufficient for synapses to make coordinated updates to learn complex, nonlinear reward-based learning tasks. We design a new deep Q-learning algorithm, Artificial Dopamine, to computationally demonstrate that synchronously distributed, per-layer TD errors may be sufficient to learn surprisingly complex RL tasks. We empirically evaluate our algorithm on MinAtar, the DeepMind Control Suite, and classic control tasks, and show it often achieves comparable performance to deep RL algorithms that use backpropagation.