arXiv subjects

Marios D. Dikaiakos

Publications and source records attributed to Marios D. Dikaiakos.

12 recordsLinked to original sources

arXiv2026

To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation

The scale of online content makes hate-speech moderation challenging, while Large Language Models (LLMs) enable harmful material to be produced and adapted more easily. Moderation therefore requires efficient classifiers that can accommodate different definitions of hate speech. Recent structured decision models accept natural-language criteria and select among specified answers, raising the question of whether they can meet these requirements without task-specific training. We present HATEDECIDE, an evaluation of six decision-model configurations on four hate-speech datasets against specialized moderation, zero-shot, commercial, and supervised baselines. We examine whether supplying a dataset's definition, or decomposing it into multiple questions, improves classification, and we measure their latency and cost. We find that commercial LLMs significantly outperform all decision models on only one dataset. Supplying definitions changes up to 28\% of predictions without consistently improving classification, and decomposition significantly improves performance in only 20\% of the comparisons. On a diagnostic set of test cases, the best hosted decision model comes within 1.6 macro-F1 points of the best commercial LLM at approximately 97\% lower inference cost. These results identify opportunities for inexpensive moderation, while showing that explicit criteria and additional questions do not reliably improve classification.

cs.CL↗

arXiv2026

AgentWare: Automating the Lifecycle of Agentic Applications across the Edge-to-Cloud Continuum

Deploying LLM-enabled agentic applications across the Edge-to-Cloud continuum remains challenging due to hardware heterogeneity, deployment complexity, limited observability, and the lack of systematic evaluation methods. Existing solutions address agent development, observability, or benchmarking separately, offering limited support for the full lifecycle of distributed agentic applications. This paper presents AgentWare, an AgenticOps framework that automates the provisioning, deployment, observability, and evaluation of agentic applications across Edge-to-Cloud infrastructures. AgentWare introduces an end-to-end lifecycle pipeline that automatically prepares heterogeneous execution environments, transforms user-defined agent implementations into distributed applications, deploys agent components across the continuum, and performs unified collection of execution traces, infrastructure telemetry, and evaluation metrics. The framework further supports automated semantic evaluation through LLM-as-a-Judge workflows and generates reproducible reports covering correctness, performance, resource utilization, and energy consumption. We demonstrate the applicability of AgentWare through a distributed book assistant agent deployed across real Edge-to-Cloud infrastructure under multiple deployment and model configurations. The results show that AgentWare enables systematic experimentation and evaluation of distributed agentic applications while significantly reducing the manual effort required for deployment, instrumentation, and analysis.

cs.DC↗

arXiv2026

MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents

As LLM agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet underexplored factor. How funψtionality is decomposed into tools affects whether an agent can select the right tool and construct valid arguments. This choice is especially consequential at the edge, where resource constraints limit which models can run locally and scaling up is often not an option. We present MCP-GRANITE, an open-source extensible benchmark framework that treats tool-interface granularity as a controlled variable for MCP-based agents, evaluated under edge and IoT scenarios. It comprises 81 multi-step scenarios across 9 domains, instantiated at 4 granularity levels from fine-grained primitive tools to a single tool. We evaluate 9 locally deployed models (268M-20.9B parameters) across 8,748 trials using task completion, tool selection F1, argument accuracy, latency, and resource-usage metrics. Results show that a 4-tool interface offers the best trade-off, improving task completion by 16.4% over fine-grained primitives and 33.6% over a single monolithic tool, while nearly doubling argument accuracy. Model size is only weakly correlated with task completion and strongly with latency, while its association with argument accuracy is less robust, and a 3.2B model at the optimal granularity outperforms a 20.9B model at a mismatched one. These findings identify tool-interface granularity as a key design parameter for MCP-based agents.

cs.DC↗

arXiv2026

A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware

Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires balancing quality, latency, model footprint, and energy. This paper presents a controlled measurement study of self-hosted LLM inference across edge and near-edge deployment nodes: an NVIDIA Jetson AGX Orin and a near-edge server with CPU-only and GPU-enabled inference modes. We evaluate multiple open-weight LLMs and quantization variants using a fixed question-answering workload, and compare them against GPT-4o as a cloud-hosted accuracy and latency reference. Our benchmarking pipeline reports accuracy, model footprint, per-token decoding latency, prefill latency, and overall execution energy. The results show that GPU-enabled server execution provides the lowest compute-side latency, while Jetson Orin shows lower measured energy, consistent with its lower platform power under our setup. CPU-only execution is consistently dominated in latency for our workload and shows higher measured energy. We also show that parameter count and downloaded weight-file size alone do not reliably predict observed accuracy or latency. Finally, using Pareto-frontier analysis, we study how deployment decisions may change under possible streamed-token delivery overheads, highlighting that compute-side inference metrics alone can lead to suboptimal placement for latency-sensitive interactive web services.

cs.DC↗

arXiv2026

InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers

The rapid growth of LLM inference is shifting sustainability concerns from one-time training to continuous serving, where infrastructure decisions shape energy use, carbon emissions, water consumption, and service quality. Yet operators often need to compare deployment alternatives before large-scale infrastructure is built, making direct measurement costly, slow, and sometimes infeasible. We present InFactPlanner, a trace-driven decision-support framework for what-if analysis of sustainable AI data center deployment for LLM inference across single and geo-distributed sites. InFactPlanner combines query traces, hardware-model profiles, candidate site configurations, PUE/WUE parameters, renewable generation models, and time-varying grid carbon intensity to estimate power, energy, carbon emissions, water use, latency, and server utilization. The framework abstracts low-level serving effects into configurable hardware-model profiles, enabling rapid comparison of site selection, capacity placement, hardware, model, renewable integration, and routing choices. We validate the energy accounting pipeline by reproducing reference LLM inference energy estimates with less than 10% deviation, evaluate scalability across multiple data centers and server counts, and demonstrate scenario-driven decision analyses for hardware selection, renewable placement, geographic deployment, and carbon-aware routing. Our results show that sustainability-optimal choices can differ from latency-optimal ones, and that the carbon value of deployment depends strongly on the local grid mix.

cs.DC↗

arXiv2026

e112: A Context-Aware Mobile Emergency Communication Platform Leveraging Smartphone Sensing and Cloud Services

This paper presents e112, a context-aware mobile emergency response application designed to strengthen communication between citizens and authorities during disasters. Building on the ubiquity of smartphones, the system provides SOS requests, incident reporting, customized alerts, evacuation guidance, and moderated community interaction, supported by a cloud-based back end and an operator dashboard for situational awareness. A user-centered design approach guided our development, ensuring clarity and usability under stressful conditions. Evaluation through usability studies and technical audits demonstrated high user satisfaction, robust performance, and accessibility. The results show that a simple, well-designed mobile application can significantly enhance emergency preparedness and response, reducing risks to human life during climate change--driven emergencies.

cs.DC↗

arXiv2025

Automating Multi-Tenancy Performance Evaluation on Edge Compute Nodes

Edge Computing emerges as a promising alternative of Cloud Computing, with scalable compute resources and services deployed in the path between IoT devices and Cloud. Since virtualization techniques can be applied on Edge compute nodes, administrators can share their Edge infrastructures among multiple users, providing the so-called multi-tenancy. Even though multi-tenancy is unavoidable, it raises concerns about security and performance degradation due to resource contention in Edge Computing. For that, administrators need to deploy services with non-antagonizing profiles and explore workload co-location scenarios to enhance performance and energy consumption. Achieving this, however, requires extensive configuration, deployment, iterative testing, and analysis, an effort-intensive and time-consuming process. To address this challenge, we introduce an auto-benchmarking framework designed to streamline the analysis of multi-tenancy performance in Edge environments. Our framework includes a built-in monitoring stack and integrates with widely used benchmarking workloads, such as streaming analytics, database operations, machine learning applications, and component-based stress testing. We perform a case-driven analysis and provide valuable insights into the impact of multi-tenancy on Edge environments with different hardware configurations and diverse workloads. Finally, the implementation of our framework, along with the containerized workloads used for experimentation, is publicly available.

cs.DC↗

arXiv2025

Data-Driven Energy Modeling of Industrial IoT Systems: A Benchmarking Approach

The widespread adoption of IoT has driven the development of cyber-physical systems (CPS) in industrial environments, leveraging Industrial IoTs (IIoTs) to automate manufacturing processes and enhance productivity. The transition to autonomous systems introduces significant operational costs, particularly in terms of energy consumption. Accurate modeling and prediction of IIoT energy requirements are critical, but traditional physics- and engineering-based approaches often fall short in addressing these challenges comprehensively. In this paper, we propose a novel methodology for benchmarking and analyzing IIoT devices and applications to uncover insights into their power demands, energy consumption, and performance. To demonstrate this methodology, we develop a comprehensive framework and apply it to study an industrial CPS comprising an educational robotic arm, a conveyor belt, a smart camera, and a compute node. By creating micro-benchmarks and an end-to-end application within this framework, we create an extensive performance and power consumption dataset, which we use to train and analyze ML models for predicting energy usage from features of the application and the CPS system. The proposed methodology and framework provide valuable insights into the energy dynamics of industrial CPS, offering practical implications for researchers and practitioners aiming to enhance the efficiency and sustainability of IIoT-driven automation.

cs.RO↗

arXiv2025

Probing the Subtle Ideological Manipulation of Large Language Models

Large Language Models (LLMs) have transformed natural language processing, but concerns have emerged about their susceptibility to ideological manipulation, particularly in politically sensitive areas. Prior work has focused on binary Left-Right LLM biases, using explicit prompts and fine-tuning on political QA datasets. In this work, we move beyond this binary approach to explore the extent to which LLMs can be influenced across a spectrum of political ideologies, from Progressive-Left to Conservative-Right. We introduce a novel multi-task dataset designed to reflect diverse ideological positions through tasks such as ideological QA, statement ranking, manifesto cloze completion, and Congress bill comprehension. By fine-tuning three LLMs-Phi-2, Mistral, and Llama-3-on this dataset, we evaluate their capacity to adopt and express these nuanced ideologies. Our findings indicate that fine-tuning significantly enhances nuanced ideological alignment, while explicit prompts provide only minor refinements. This highlights the models' susceptibility to subtle ideological manipulation, suggesting a need for more robust safeguards to mitigate these risks.

cs.CL↗

arXiv2025

Large Language Models For Text Classification: Case Study And Comprehensive Review

Unlocking the potential of Large Language Models (LLMs) in data classification represents a promising frontier in natural language processing. In this work, we evaluate the performance of different LLMs in comparison with state-of-the-art deep-learning and machine-learning models, in two different classification scenarios: i) the classification of employees' working locations based on job reviews posted online (multiclass classification), and 2) the classification of news articles as fake or not (binary classification). Our analysis encompasses a diverse range of language models differentiating in size, quantization, and architecture. We explore the impact of alternative prompting techniques and evaluate the models based on the weighted F1-score. Also, we examine the trade-off between performance (F1-score) and time (inference response time) for each language model to provide a more nuanced understanding of each model's practical applicability. Our work reveals significant variations in model responses based on the prompting strategies. We find that LLMs, particularly Llama3 and GPT-4, can outperform traditional methods in complex classification tasks, such as multiclass classification, though at the cost of longer inference times. In contrast, simpler ML models offer better performance-to-time trade-offs in simpler binary classification tasks.

cs.CL↗

arXiv2019

Check-It: A Plugin for Detecting and Reducing the Spread of Fake News and Misinformation on the Web

Over the past few years, we have been witnessing the rise of misinformation on the Web. People fall victims of fake news during their daily lives and assist their further propagation knowingly and inadvertently. There have been many initiatives that are trying to mitigate the damage caused by fake news, focusing on signals from either domain flag-lists, online social networks or artificial intelligence. In this work, we present Check-It, a system that combines, in an intelligent way, a variety of signals into a pipeline for fake news identification. Check-It is developed as a web browser plugin with the objective of efficient and timely fake news detection, respecting the user's privacy. Experimental results show that Check-It is able to outperform the state-of-the-art methods. On a dataset, consisting of 9 millions of articles labeled as fake and real, Check-It obtains classification accuracies that exceed 99%.

cs.SI↗

arXiv2011

The Dynamics of Vehicular Networks in Urban Environments

Vehicular Ad hoc NETworks (VANETs) have emerged as a platform to support intelligent inter-vehicle communication and improve traffic safety and performance. The road-constrained, high mobility of vehicles, their unbounded power source, and the emergence of roadside wireless infrastructures make VANETs a challenging research topic. A key to the development of protocols for inter-vehicle communication and services lies in the knowledge of the topological characteristics of the VANET communication graph. This paper explores the dynamics of VANETs in urban environments and investigates the impact of these findings in the design of VANET routing protocols. Using both real and realistic mobility traces, we study the networking shape of VANETs under different transmission and market penetration ranges. Given that a number of RSUs have to be deployed for disseminating information to vehicles in an urban area, we also study their impact on vehicular connectivity. Through extensive simulations we investigate the performance of VANET routing protocols by exploiting the knowledge of VANET graphs analysis.

cs.OH↗