Large Language Models (LLMs) have transformed Recommendation Systems (RecSys) by enabling more user-aware interactions. However, this shift raises new challenges in evaluating fairness, particularly due to confounding systemic biases such as popularity bias. Conventional fairness assessments often confuse disparities in user treatment with systemic biases toward popular items, resulting in misleading conclusions. In this paper, we introduce PureBiasoMeter, a diagnostic framework that decouples popularity bias from user-level fairness in LLM-based RecSys. Our approach is based on the hypothesis that accurate fairness evaluation requires first mitigating popularity bias and then remeasuring fairness metrics. We generate a comprehensive set of 72 prompts using different user profiling strategies, demographic variants, and bias mitigation instructions. By applying these prompts in a black-box LLM setting, we evaluate fairness sensitivity, recommendation quality, and bias levels across multiple dimensions. Our results demonstrate that removing popularity bias substantially alters fairness measurements and reveals underlying disparities that were previously unknown. PureBiasoMeter thus provides a more reliable basis for fairness analysis and contributes a practical tool for disentangling intertwined sources of bias in modern RecSys.

The cost of using cloud storage services is complex and often an unclear structure, while it is one of the important factors for organisations adopting cloud storage. Furthermore, organisations take advantage of multi-cloud or hybrid solutions to combine multiple public and/or private cloud service providers to avoid vendor lock-in, achieve high availability and performance, optimise cost, etc. This complicated ecosystem makes it even harder to understand and manage cost. Therefore, in this paper, we provide a taxonomy of cloud storage cost in order to provide a better understanding and insights on this complex problem domain.

Cloud service providers offer application providers with virtually infinite storage and computing resources, while providing cost-efficiency and various other quality of service (QoS) properties through a storage-as-a-service (StaaS) approach. Organizations also use multi-cloud or hybrid solutions by combining multiple public and/or private cloud service providers to avoid vendor lock-in, achieve high availability and performance, and optimise cost. Indeed cost is one of the important factors for organizations while adopting cloud storage; however, cloud storage providers offer complex pricing policies, including the actual storage cost and the cost related to additional services (e.g., network usage cost). In this article, we provide a detailed taxonomy of cloud storage cost and a taxonomy of other QoS elements, such as network performance, availability, and reliability. We also discuss various cost trade-offs, including storage and computation, storage and cache, and storage and network. Finally, we provide a cost comparison across different storage providers under different contexts and a set of user scenarios to demonstrate the complexity of cost structure and discuss existing literature for cloud storage selection and cost optimization. We aim that the work presented in this article will provide decision-makers and researchers focusing on cloud storage selection for data placement, cost modelling, and cost optimization with a better understanding and insights regarding the elements contributing to the storage cost and this complex problem domain.

Cloud storage adoption has increased over the years given the high demand for fast processing, low access latency, and ever-increasing amount of data being generated by, e.g., Internet of Things applications. In order to meet the users’ demands and provide a cost-effective solution, cloud service providers offer tiered storage; however, keeping the data in one tier is not cost-effective. In this respect, cloud storage tier optimization involves aligning data storage needs with the most suitable and cost-effective storage tier, thus reducing costs while ensuring data availability and meeting performance requirements. Ideally, this process considers the trade-off between performance and cost, as different storage tiers offer different levels of performance and durability. It also encompasses data lifecycle management, where data is automatically moved between tiers based on access patterns, which in turn impacts the storage cost. In this respect, this article explores two novel classification approaches, rule-based and game theory-based, to optimize cloud storage cost by reassigning data between different storage tiers. Four distinct storage tiers are considered: premium, hot, cold, and archive. The viability and potential of the proposed approaches are demonstrated by comparing cost savings and analyzing the computational cost using both fully-synthetic and semi-synthetic datasets with static and dynamic access patterns. The results indicate that the proposed approaches have the potential to significantly reduce cloud storage cost, while being computationally feasible for practical applications. Both approaches are lightweight and industry- and platform-independent.

Cloud computing has become popular among individuals and enterprises due to its convenience, scalability, and flexibility. However, a major concern for many cloud service users is the rising cost of cloud resources. Since cloud computing uses a pay-per-use model, costs can add up quickly, and unexpected expenses can arise from a lack of visibility and control. The cost structure gets even more complicated when working with multi-cloud or hybrid environments. Businesses may spend much of their IT budget on cloud computing, and any savings can improve their competitiveness and financial stability. Hence, an efficient cloud cost management is crucial. To overcome this difficulty, new approaches and tools are being developed to provide greater oversight and command over cloud a graph-based approach for modelling cost elements and cloud resources and a potential way to solve the resulting constraint problem of cost optimisation. In this context, we primarily consider utilisation, cost, performance, and availability. The proposed approach is evaluated on three different user scenarios, and results indicate that it could be effective in cost modelling, cost optimisation, and scalability. This approach will eventually help organisations make informed decisions about cloud resource placement and manage the costs of software applications and data workflows deployed in single, hybrid, or multi-cloud environments.

Zero-shot relation extraction (RE) presents the challenge of identifying entity relationships from text without training on those specific relations. Despite significant advancements in natural language processing by applying large language models (LLMs), their application to zero-shot RE remains less effective compared to traditional models that fine-tune smaller pre-trained language models. This limitation is attributed to insufficient prompting strategies that fail to leverage the full capabilities of LLMs for zero-shot RE, considering the intrinsic complexities of the RE task. A compelling question is whether LLMs can address complex tasks, such as RE, by decomposing them into more straightforward, distinct tasks that are easier to manage and solve individually. We propose the Refine-Estimate-Answer (REA) approach to answer this question. This multi-stage prompting strategy of REA decomposes the RE task into more manageable subtasks and applies iterative refinement to guide LLMs through the complex reasoning required for accurate RE. Our research validates the effectiveness of REA through comprehensive testing across multiple public RE datasets, demonstrating marked improvements over existing LLM-based frameworks. Experimental results on the FewRel, Wiki-ZSL, and TACRED datasets show that our proposed approach significantly boosts the vanilla prompting F1 scores by 31.57, 19.52, and 15.39, respectively, thereby outperforming the performance of state-of-the-art LLM-based methods.

Prompt-tuning and instruction-tuning of language models have exhibited significant results in few-shot Natural Language Processing (NLP) tasks, such as Relation Extraction (RE), which involves identifying relationships between entities within a sentence. However, the effectiveness of these methods relies heavily on the design of the prompts. A compelling question is whether incorporating external knowledge can enhance the language model's understanding of NLP tasks. In this paper, we introduce wiki-based prompt construction that leverages Wikidata as a source of information to craft more informative prompts for both prompt-tuning and instruction-tuning of language models in RE. Our experiments show that using wiki-based prompts enhances cutting-edge language models in RE, emphasizing their potential for improving RE tasks. Our code and datasets are available at GitHub 1

The generation of a robot program can be seen as a collection of sub-problems, where many combinations of some of these sub-problems are well studied. The performance of a robot program is strongly conditioned by the location of the tasks. However, the scope of previous methods does not include workspace layout design, likely missing high-quality solutions. In industrial applications, designing robot workspace layout is part of the commissioning. We broaden the scope and show how to model a dual-arm multi-tool robot assembly problem. Our model includes more robot programming sub-problems than previous methods, as well as workspace layout design. We propose a constraint programming formulation in MiniZinc that includes elements from scheduling and routing, extended with variable task locations. We evaluate the model on realistic assembly problems and workspaces, utilizing the dual-arm YuMi robot from ABB Ltd. We also evaluate redundant constraints and various formulations for avoiding arm-to-arm collisions. The best model variant quickly finds high-quality solutions for all problem instances. This demonstrates the potential of our approach as a valuable tool for a robot programmer.

The emerging concept of big data pipelines provides relevant solutions and is one of the main enablers of telemedicine. We present a data pipeline for remote patient monitoring and show a real-world example of how data pipelines help address the stringent requirements of telemedicine.

Prompt-based language models have produced encouraging results in numerous applications, including Named Entity Recognition (NER) tasks. NER aims to identify entities in a sentence and provide their types. However, the strong performance of most available NER approaches is heavily dependent on the design of discrete prompts and a verbalizer to map the model-predicted outputs to entity categories, which are complicated undertakings. To address these challenges, we present ContrastNER, a prompt-based NER framework that employs both discrete and continuous tokens in prompts and uses a contrastive learning approach to learn the continuous prompts and forecast entity types. The experimental results demonstrate that ContrastNER obtains competitive performance to the state-of-the-art NER methods in high-resource settings and outperforms the state-of-the-art models in low-resource circumstances without requiring extensive manual prompt engineering and verbalizer design.