Ontology-based data management and knowledge graphs have emerged in recent years as efficient approaches for managing and utilizing diverse and large data sets. In this regard, research on algorithms for automatic semantic labeling and modeling as a prerequisite for both has made steady progress in the form of new approaches. The range of algorithms varies in the type of information used (data schema, values, or metadata), as well as in the underlying methodology (e.g., use of different machine learning methods or external knowledge bases). Approaches that have been established over the years, however, still come with various weaknesses. Most approaches are evaluated on few small data corpora specific to the approach. This reduces comparability and also limits statements for the general applicability and performance of those approaches. Other research areas, such as computer vision or natural language processing solve this problem by providing unified data corpora for the evaluation of specific algorithms and tasks. In this paper, we present and publish VC-SLAM to lay the necessary foundation for future research. This corpus allows the evaluation and comparison of semantic labeling and modeling approaches across different methodologies, and it is the first corpus that additionally allows to leverage textual data documentations for semantic labeling and modeling. Each of the contained 101 data sets consists of labels, data and metadata, as well as corresponding semantic labels and a semantic model that were manually created by human experts using an ontology that was explicitly built for the corpus. We provide statistical information about the corpus as well as a critical discussion of its strengths and shortcomings, and test the corpus with existing methods for labeling and modeling.
Enhancing fuel efficiency in public transportation requires the integration of complex multimodal data into interpretable, decision-relevant insights. However, traditional analytics and visualization methods often yield fragmented outputs that demand extensive human interpretation, limiting scalability and consistency. This study presents a multi-agent framework that leverages multimodal large language models (LLMs) to automate data narration and energy insight generation. The framework coordinates three specialized agents, including a data narration agent, an LLM-as-a-judge agent, and an optional human-in-the-loop evaluator, to iteratively transform analytical artifacts into coherent, stakeholder-oriented reports. The system is validated through a real-world case study on public bus transportation in Northern Jutland, Denmark, where fuel efficiency data from 4006 trips are analyzed using Gaussian Mixture Model clustering. Comparative experiments across five state-of-the-art LLMs and three prompting paradigms identify GPT-4.1 mini with Chain-of-Thought prompting as the optimal configuration, achieving 97.3% narrative accuracy while balancing interpretability and computational cost. The findings demonstrate that multi-agent orchestration significantly enhances factual precision, coherence, and scalability in LLM-based reporting. The proposed framework establishes a replicable and domain-adaptive methodology for AI-driven narrative generation and decision support in energy informatics.
The heterogeneity of data poses a great challenge when data from different sources is to be merged for one application. Solutions for this are offered, for example, by ontology-based data management (OBDM). A challenge of OBDM is the automatic creation of semantic models from datasets. This process is typically performed either data- or label-driven and always involves manual human intervention. We identified textual descriptions of data, a form of metadata, quickly to be produced and consumed by humans, as third possible basis for automatic semantic modelling. In this paper, we present, how we plan to use textual descriptions to enhance semantic data management. We will use state of the art NLP technologies to identify concepts within textual descriptions and build semantic models from this in combination with an evolving ontology. We will use automatically identified models in combination with the human data provider to automatically extend the ontology so that it learns new verified concepts over time. Finally, we will use the created ontology and automatically identified semantic models to either rate descriptions for new data sources or even to automatically generate descriptive texts that are easier to understand by the human user than formal models. We present the procedure which we plan for the ongoing research, as well as expected outcomes.
Enhancing fuel efficiency in public transportation requires the integration of complex multimodal data into interpretable, decision-relevant insights. However, traditional analytics and visualization methods often yield fragmented outputs that demand extensive human interpretation, limiting scalability and consistency. This study presents a multi-agent framework that leverages multimodal large language models (LLMs) to automate data narration and energy insight generation. The framework coordinates three specialized agents, including a data narration agent, an LLM-as-a-judge agent, and an optional human-in-the-loop evaluator, to iteratively transform analytical artifacts into coherent, stakeholder-oriented reports. The system is validated through a real-world case study on public bus transportation in Northern Jutland, Denmark, where fuel efficiency data from 4006 trips are analyzed using Gaussian Mixture Model clustering. Comparative experiments across five state-of-the-art LLMs and three prompting paradigms identify GPT-4.1 mini with Chain-of-Thought prompting as the optimal configuration, achieving 97.3% narrative accuracy while balancing interpretability and computational cost. The findings demonstrate that multi-agent orchestration significantly enhances factual precision, coherence, and scalability in LLM-based reporting. The proposed framework establishes a replicable and domain-adaptive methodology for AI-driven narrative generation and decision support in energy informatics.