arXiv subjects

Matthijs Jansen op de Haar

Publications and source records attributed to Matthijs Jansen op de Haar.

6 recordsLinked to original sources

arXiv2026

GuidedRAG: Semantic Steering of Retrieval-Augmented Generation

In this work, we propose GuidedRAG, a novel extension to traditional Retrieval-Augmented Generation (RAG) that introduces a dedicated selection stage and semantic steering during retrieval. In contrast to current state-of-the-art RAG approaches, which depend on increasingly complex retrieval and knowledge structures, GuidedRAG constrains the knowledge base using semantics before retrieval, aligning the retrieval space with user intent while substantially reducing the search space. Our evaluation shows that GuidedRAG improves retrieval relevance by 14.0-15.8%, mitigates a 19.7-27.4% loss in retrieval precision, and reduces retrieval overhead by orders of magnitude. Moreover, relevant chunks are consistently retrieved earlier in the ranking process, while alignment with user intent improves by 31.8-36.8%. We further show that GuidedRAG achieves full coverage across 15 diverse RAG variants, demonstrating generalizability across the literature. Together, these findings establish semantic steering and selections as a powerful and generalizable paradigm for improving the current state-of-the-art in RAG.

cs.IR↗

arXiv2026

All Relations Lead to Rome: Automated Knowledge Graph Creation and Question Generation

Large language models have substantially improved information retrieval and question answering; however, existing datasets generally support either vector-based retrieval over unstructured text or reasoning over knowledge graphs, without providing a unified representation that combines both paradigms. Moreover, current benchmarks rarely provide ground-truth entities, relations, and fact-grounded question-answer pairs aligned with the underlying corpus. To address this gap, we introduce All Relations Lead to Rome (ARLtR), a unified framework for automated knowledge graph construction and fact-grounded question-answer generation. ARLtR jointly constructs a knowledge graph, embeddings, and question-answer pairs that are explicitly grounded in extracted entities, relations, and supporting textual evidence. We further instantiate the framework as a historical dataset centered on the Roman Empire, comprising over 19,000 entities, 16,000 chunks, and 8,400 question-answer pairs (https://huggingface.co/datasets/FaynePro/all-relations-lead-to-rome). By tightly coupling symbolic graph representations with dense retrieval representations, ARLtR facilitates the evaluation and development of hybrid retrieval systems and semantic steering approaches within a single coherent resource.

cs.IR↗

arXiv2026

Beyond Grading Accuracy: Exploring Alignment of TAs and LLMs

In this paper, we investigate the potential of open-source Large Language Models (LLMs) for grading Unified Modeling Language (UML) class diagrams. In contrast to existing work, which primarily evaluates proprietary LLMs, we focus on non-proprietary models, making our approach suitable for universities where transparency and cost are critical. Additionally, existing studies assess performance over complete diagrams rather than individual criteria, offering limited insight into how automated grading aligns with human evaluation. To address these gaps, we propose a grading pipeline in which student-generated UML class diagrams are independently evaluated by both teaching assistants (TAs) and LLMs. Grades are then compared at the level of individual criteria. We evaluate this pipeline through a quantitative study of 92 UML class diagrams from a software design course, comparing TA grades against assessments produced by six open-source LLMs. Performance is measured across individual criteria, highlighting areas where LLMs diverge from human graders. Our results show per-criterion accuracy of up to 88.56\% and a Pearson correlation coefficient of up to 0.78, representing a substantial improvement over previous work while using only open-source models. The models achieve performance close to that of a TA, suggesting a possible path toward a mixed-initiative grading system, where TAs are aided in their grading. Our findings demonstrate that open-source LLMs can effectively support UML class diagram grading by explicitly identifying alignment with grading criteria. The proposed pipeline provides a practical approach to managing increasing workloads with growing student counts.

cs.CY↗

arXiv2026

Digital Twin-Based Simulation for Predictive Decision-Making in Waterway Logistics

This paper investigates the potential of a Digital Twin (DT) for freight routing across inland waterway networks under uncertain water-level conditions. Existing approaches insufficiently account for increasing climate-induced volatility in water levels, which often result in higher operational costs and emissions due to the need for more expensive transport alternatives, such as road transport. These existing methods often rely on reactive countermeasures to remain resilient. To address these limitations, six interviews with experts in domains related to inland shipping were conducted to identify three common contingency scenarios and appropriate operational responses. These scenarios were subsequently incorporated into a time-sliced simulation environment in which predictive decision-making, enabled by a DT environment, was compared against reactive approaches. The results demonstrate that predictive modeling substantially reduces operational costs and modal shifts at prediction accuracies between 70% and 100%, despite extreme conditions. In addition, the predictive model achieves an average 28.3% reduction in fuel-related costs by reducing the total distance ships travel. The simulation outcomes were evaluated together with domain experts to assess the practical relevance and applicability of the proposed DT-enabled approach.

cs.CY↗

arXiv2025

A Design Space for Intelligent Agents in Mixed-Initiative Visual Analytics

Mixed-initiative visual analytics (VA) systems, where human and artificial intelligence (AI) agents collaborate as equal partners during analysis, represented a paradigm shift in human-computer interaction. With recent advances in AI, these systems have seen an increase in sophisticated software agents that have improved task planning, reasoning, and completion capabilities. However, while existing work characterizes agent interplay and communication strategies, there is a limited understanding of the overarching design principles for intelligent agents. Through a systematic review of 90 systems (and 207 unique agents), we propose a design space of intelligent agents comprising six dimensions that collectively characterize an agent's perception, environmental understanding, action capability, and communication strategies. We contribute a novel framework for researchers and designers to explore various design choices for new systems and to situate a system in the current landscape. We conclude with future research opportunities for intelligent agents in mixed-initiative VA systems.

cs.HC↗

arXiv2025

SemanticTours: A Conceptual Framework for Non-Linear, Knowledge Graph-Driven Data Tours

Interactive tours help users explore datasets and provide onboarding. They rely on a linear sequence of views, showing a curated set of relevant data selections and introduce user interfaces. Existing frameworks of tours, however, often do not allow for branching and refining hypotheses outside of a rigid sequence, which is important in knowledge-centric domains such as law. For example, lawyers performing analytical case analysis need to iteratively weigh up different legal norms and construct strings of arguments. To address this gap, we propose SemanticTours, a semantic, graph-based model of tours that shifts from a sequence-based towards a graph-based navigation. Our model constructs a domain-specific knowledge graph that connects data elements based on user-definable semantic relationships. These relationships enable non-linear graph navigation that defines tours. We apply SemanticTours to the domain of law and conceptualize a visual analytics design and interaction concept for analytical reasoning in legal case analysis. Our concept accounts for the inherent complexity of graph-based tours using aggregated graph nodes and supporting navigation with a semantic lens. During an evaluation with six domain experts from law, they suggest that graph-based tours better support their analytical reasoning than sequences. Our work opens research opportunities for such tours to support analytical reasoning in law and other knowledge-centric domains.

cs.HC↗