Michael Martin

Lars-Peter Meyer, Claus Stadler, Johannes Frey et al.

Knowledge Graphs (KG) provide us with a structured, flexible, transparent, cross-system, and collaborative way of organizing our knowledge and data across various domains in society and industrial as well as scientific disciplines. KGs surpass any other form of representation in terms of effectiveness. However, Knowledge Graph Engineering (KGE) requires in-depth experiences of graph structures, web technologies, existing models and vocabularies, rule sets, logic, as well as best practices. It also demands a significant amount of work. Considering the advancements in large language models (LLMs) and their interfaces and applications in recent years, we have conducted comprehensive experiments with ChatGPT to explore its potential in supporting KGE. In this paper, we present a selection of these experiments and their results to demonstrate how ChatGPT can assist us in the development and management of KGs.

Karishma Mohiuddin, Mirza Ariful Alam, Mirza Mohtashim Alam et al.

Skilled employees are the most important pillars of an organization. Despite this, most organizations face high attrition and turnover rates. While several machine learning models have been developed to analyze attrition and its causal factors, the interpretations of those models remain opaque. In this paper, we propose the HR-DSS approach, which stands for Human Resource (HR) Decision Support System, and uses explainable AI for employee attrition problems. The system is designed to assist HR departments in interpreting the predictions provided by machine learning models. In our experiments, we employ eight machine learning models to provide predictions. We further process the results achieved by the best-performing model by the SHAP explainability process and use the SHAP values to generate natural language explanations which can be valuable for HR. Furthermore, using "What-if-analysis", we aim to observe plausible causes for attrition of an individual employee. The results show that by adjusting the specific dominant features of each individual, employee attrition can turn into employee retention through informative business decisions.

Lars-Peter Meyer, Johannes Frey, Kurt Junghanns et al.

As the field of Large Language Models (LLMs) evolves at an accelerated pace, the critical need to assess and monitor their performance emerges. We introduce a benchmarking framework focused on knowledge graph engineering (KGE) accompanied by three challenges addressing syntax and error correction, facts extraction and dataset generation. We show that while being a useful tool, LLMs are yet unfit to assist in knowledge graph generation with zero-shot prompting. Consequently, our LLM-KG-Bench framework provides automatic evaluation and storage of LLM responses as well as statistical data and visualization tools to support tracking of prompt engineering and model performance.

Vesa Akerman, David Baines, Damien Daspit et al.

Efficiently and accurately translating a corpus into a low-resource language remains a challenge, regardless of the strategies employed, whether manual, automated, or a combination of the two. Many Christian organizations are dedicated to the task of translating the Holy Bible into languages that lack a modern translation. Bible translation (BT) work is currently underway for over 3000 extremely low resource languages. We introduce the eBible corpus: a dataset containing 1009 translations of portions of the Bible with data in 833 different languages across 75 language families. In addition to a BT benchmarking dataset, we introduce model performance benchmarks built on the No Language Left Behind (NLLB) neural machine translation (NMT) models. Finally, we describe several problems specific to the domain of BT and consider how the established data and model benchmarks might be used for future translation efforts. For a BT task trained with NLLB, Austronesian and Trans-New Guinea language families achieve 35.1 and 31.6 BLEU scores respectively, which spurs future innovations for NMT for low-resource languages in Papua New Guinea.

Lars-Peter Meyer, Johannes Frey, Desiree Heim et al.

Current Large Language Models (LLMs) can assist developing program code beside many other things, but can they support working with Knowledge Graphs (KGs) as well? Which LLM is offering the best capabilities in the field of Semantic Web and Knowledge Graph Engineering (KGE)? Is this possible to determine without checking many answers manually? The LLM-KG-Bench framework in Version 3.0 is designed to answer these questions. It consists of an extensible set of tasks for automated evaluation of LLM answers and covers different aspects of working with semantic technologies. In this paper the LLM-KG-Bench framework is presented in Version 3 along with a dataset of prompts, answers and evaluations generated with it and several state-of-the-art LLMs. Significant enhancements have been made to the framework since its initial release, including an updated task API that offers greater flexibility in handling evaluation tasks, revised tasks, and extended support for various open models through the vllm library, among other improvements. A comprehensive dataset has been generated using more than 30 contemporary open and proprietary LLMs, enabling the creation of exemplary model cards that demonstrate the models' capabilities in working with RDF and SPARQL, as well as comparing their performance on Turtle and JSON-LD RDF serialization tasks.

Ling Sun, Peter Sullivan, Michael Martin et al.

Quantum natural language processing (QNLP) offers a novel approach to semantic modeling by embedding compositional structure directly into quantum circuits. This paper investigates the application of QNLP models to the task of Natural Language Inference (NLI), comparing quantum, hybrid, and classical transformer-based models under a constrained few-shot setting. Using the lambeq library and the DisCoCat framework, we construct parameterized quantum circuits for sentence pairs and train them for both semantic relatedness and inference classification. To assess efficiency, we introduce a novel information-theoretic metric, Information Gain per Parameter (IGPP), which quantifies learning dynamics independent of model size. Our results demonstrate that quantum models achieve performance comparable to classical baselines while operating with dramatically fewer parameters. The Quantum-based models outperform randomly initialized transformers in inference and achieve lower test error on relatedness tasks. Moreover, quantum models exhibit significantly higher per-parameter learning efficiency (up to five orders of magnitude more than classical counterparts), highlighting the promise of QNLP in low-resource, structure-sensitive settings. To address circuit-level isolation and promote parameter sharing, we also propose a novel cluster-based architecture that improves generalization by tying gate parameters to learned word clusters rather than individual tokens.

Sara Todorovikj, Lars-Peter Meyer, Michael Martin

Large Language Models (LLMs) are increasingly used for tasks involving Knowledge Graphs (KGs), whose evaluation typically focuses on accuracy and output correctness. We propose a complementary task characterization approach using three complexity frameworks from cognitive psychology. Applying this to the LLM-KG-Bench framework, we highlight value distributions, identify underrepresented demands and motivate richer interpretation and diversity for benchmark evaluation tasks.

Lisa Wenige, Claus Stadler, Michael Martin et al.

This paper presents a framework for assessing data and metadata quality within Open Data portals. Although a few benchmark frameworks already exist for this purpose, they are not yet detailed enough in both breadth and depth to make valid statements about the actual discoverability and accessibility of publicly available data collections. To address this research gap, we have designed a quality framework that is able to evaluate data quality in Open Data portals on dedicated and fine-grained dimensions, such as interoperability, findability, uniqueness or completeness. Additionally, we propose quality measures that allow for valid assessments regarding cross-portal findability and uniqueness of dataset descriptions. We have validated our novel quality framework for the German Open Data landscape and found out that metadata often still lacks meaningful descriptions and is not yet extensively connected to the Semantic Web.

Paul Hubbard, Alexander Kott, Michael Martin

The models in this paper demonstrate how self-reinforcing error due to positive feedback can lead to overload and saturation of decision-making elements, and ultimately the cascading collapse of an organization due to the propagation of overload and erroneous decisions throughout the organization. We begin the paper with an analysis of the stability of the decision-making aspects of command organizations from a system-theoretic perspective. A simple dynamic model shows how an organization can enter into a self-reinforcing cycle of increasing decision workload until the demand for decisions exceeds the decision-making capacity of the organization. We then extend the model to more complex networked organizations and show that they also experience a form of self-reinforcing degradation. In particular, we find that the degradation in decision quality has a tendency to propagate through the hierarchical structure, i.e. overload at one location affects other locations by overloading the higher-level components which then in turn overload their subordinates. Our computational experiments suggest several strategies for mitigating this type of malfunction: dumping excessive load, empowering lower echelons, minimizing the need for coordination, using command-by-negation, insulating weak performers, and applying on-line diagnostics. We describe a method to allocate decision responsibility and arrange information flow dynamically within a team of decision-makers for command and control.