arXiv subjects

Jan Mendling

Publications and source records attributed to Jan Mendling.

At least 19 recordsLinked to original sources

arXiv2026

Simulating Eating Disorder Patients with LLMs: Evaluating Psychological Persona Stability in Multi-Turn Conversations

Large language model (LLM)-based simulations of clinical patients are increasingly used for research and training, yet their validity requires persona stability: coherent maintenance of an assigned psychological profile across and within conversations. We evaluate this prerequisite using eating disorder personas grounded in five published case vignettes, a dual-assessment framework (self-report + independent observer ratings), and validated psychometric instruments (EDE-Q) with known ground-truth scores. Across six LLMs and two experiments (between-conversation stability (Exp. I) and within-conversation stability (Exp. II)), we find that LLMs are paradoxically too stable and too inaccurate: variability is negligible, yet all models systematically overshoot ground-truth severity by 12-30% of the scale range (0.7-1.8 points on a 0-6 scale). The mechanism is selective stereotyping: models differentiate cases on behavioural items (dietary restraint) but maximise cognitive-affective items (body dissatisfaction, weight preoccupation) at ceiling regardless of case severity. Additional conversational context does not improve accuracy; it compounds the overshoot. LLMs can portray severe eating pathology but lack a representation of moderate clinical presentations, a "missing middle".

cs.CY↗

arXiv2026

Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks

How much of LLM output variance is explained by prompts versus model choice versus stochasticity through sampling? We answer this by evaluating 12 LLMs on 10 creativity prompts with 100 samples each (N = 12,000). For output quality (originality), prompts explain 36.43% of variance, comparable to model choice (40.94%). But for output quantity (fluency), model choice (51.25%) and within-LLM variance (33.70%) dominate, with prompts explaining only 4.22%. Prompts are powerful levers for steering output quality, but given the substantial within-LLM variance (10-34%), single-sample evaluations risk conflating sampling noise with genuine prompt or model effects.

cs.AI↗

arXiv2026

Fairness in Healthcare Processes: A Quantitative Analysis of Decision Making in Triage

Fairness in automated decision-making has become a critical concern, particularly in high-pressure healthcare scenarios such as emergency triage, where fast and equitable decisions are essential. Process mining is increasingly investigating fairness. There is a growing area focusing on fairness-aware algorithms. So far, we know less how these concepts perform on empirical healthcare data or how they cover aspects of justice theory. This study addresses this research problem and proposes a process mining approach to assess fairness in triage by linking real-life event logs with conceptual dimensions of justice. Using the MIMICEL event log (as derived from MIMIC-IV ED), we analyze time, re-do, deviation and decision as process outcomes, and evaluate the influence of age, gender, race, language and insurance using the Kruskal-Wallis, Chi-square and effect size measurements. These outcomes are mapped to justice dimensions to support the development of a conceptual framework. The results demonstrate which aspects of potential unfairness in high-acuity and sub-acute surface. In this way, this study contributes empirical insights that support further research in responsible, fairness-aware process mining in healthcare.

cs.CY↗

arXiv2025

Cross-Organizational Analysis of Parliamentary Processes: A Case Study

Process Mining has been widely adopted by businesses and has been shown to help organizations analyze and optimize their processes. However, so far, little attention has gone into the cross-organizational comparison of processes, since many companies are hesitant to share their data. In this paper, we explore the processes of German state parliaments that are often legally required to share their data and run the same type of processes for different geographical regions. This paper is the first attempt to apply process mining to parliamentary processes and, therefore, contributes toward a novel interdisciplinary research area that combines political science and process mining. In our case study, we analyze legislative processes of three German state parliaments and generate insights into their differences and best practices. We provide a discussion of the relevance of our results that are based on knowledge exchange with a political scientist and a domain expert from the German federal parliament.

cs.DB↗

arXiv2025

Transforming Football Data into Object-centric Event Logs with Spatial Context Information

Object-centric event logs expand the conventional single-case notion event log by considering multiple objects, allowing for the analysis of more complex and realistic process behavior. However, the number of real-world object-centric event logs remains limited, and further studies are needed to test their usefulness. The increasing availability of data from team sports can facilitate object-centric process mining, leveraging both real-world data and suitable use cases. In this paper, we present a framework for transforming football (soccer) data into an object-centric event log, further enhanced with a spatial dimension. We demonstrate the effectiveness of our framework by generating object-centric event logs based on real-world football data and discuss the results for varying process representations. With our paper, we provide the first example for object-centric event logs in football analytics. Future work should consider variant analysis and filtering techniques to better handle variability

cs.DB↗

arXiv2025

The Impact of Event Data Partitioning on Privacy-aware Process Discovery

Information systems support the execution of business processes. The event logs of these executions generally contain sensitive information about customers, patients, and employees. The corresponding privacy challenges can be addressed by anonymizing the event logs while still retaining utility for process discovery. However, trading off utility and privacy is difficult: the higher the complexity of event log, the higher the loss of utility by anonymization. In this work, we propose a pipeline that combines anonymization and event data partitioning, where event abstraction is utilized for partitioning. By leveraging event abstraction, event logs can be segmented into multiple parts, allowing each sub-log to be anonymized separately. This pipeline preserves privacy while mitigating the loss of utility. To validate our approach, we study the impact of event partitioning on two anonymization techniques using three real-world event logs and two process discovery techniques. Our results demonstrate that event partitioning can bring improvements in process discovery utility for directly-follows-based anonymization techniques.

cs.CR↗

arXiv2025

Process Mining on Distributed Data Sources

Major domains such as logistics, healthcare, and smart cities increasingly rely on sensor technologies and distributed infrastructures to monitor complex processes in real time. These developments are transforming the data landscape from discrete, structured records stored in centralized systems to continuous, fine-grained, and heterogeneous event streams collected across distributed environments. As a result, traditional process mining techniques, which assume centralized event logs from enterprise systems, are no longer sufficient. In this paper, we discuss the conceptual and methodological foundations for this emerging field. We identify three key shifts: from offline to online analysis, from centralized to distributed computing, and from event logs to sensor data. These shifts challenge traditional assumptions about process data and call for new approaches that integrate infrastructure, data, and user perspectives. To this end, we define a research agenda that addresses six interconnected fields, each spanning multiple system dimensions. We advocate a principled methodology grounded in algorithm engineering, combining formal modeling with empirical evaluation. This approach enables the development of scalable, privacy-aware, and user-centric process mining techniques suitable for distributed environments. Our synthesis provides a roadmap for advancing process mining beyond its classical setting, toward a more responsive and decentralized paradigm of process intelligence.

cs.ET↗

arXiv2025

Sustainability via LLM Right-sizing

Large language models (LLMs) have become increasingly embedded in organizational workflows. This has raised concerns over their energy consumption, financial costs, and data sovereignty. While performance benchmarks often celebrate cutting-edge models, real-world deployment decisions require a broader perspective: when is a smaller, locally deployable model "good enough"? This study offers an empirical answer by evaluating eleven proprietary and open-weight LLMs across ten everyday occupational tasks, including summarizing texts, generating schedules, and drafting emails and proposals. Using a dual-LLM-based evaluation framework, we automated task execution and standardized evaluation across ten criteria related to output quality, factual accuracy, and ethical responsibility. Results show that GPT-4o delivers consistently superior performance but at a significantly higher cost and environmental footprint. Notably, smaller models like Gemma-3 and Phi-4 achieved strong and reliable results on most tasks, suggesting their viability in contexts requiring cost-efficiency, local deployment, or privacy. A cluster analysis revealed three model groups -- premium all-rounders, competent generalists, and limited but safe performers -- highlighting trade-offs between quality, control, and sustainability. Significantly, task type influenced model effectiveness: conceptual tasks challenged most models, while aggregation and transformation tasks yielded better performances. We argue for a shift from performance-maximizing benchmarks to task- and context-aware sufficiency assessments that better reflect organizational priorities. Our approach contributes a scalable method to evaluate AI models through a sustainability lens and offers actionable guidance for responsible LLM deployment in practice.

cs.CL↗

arXiv2025

Towards a Theory on Process Automation Effects

Process automation is a crucial strategy for improving business processes, but little attention has been paid to the effects that automation has once it is operational. This paper addresses this research problem by reviewing the literature on human-automation interaction. Although many of the studies in this field have been conducted in different domains, they provide a foundation for developing propositions about process automation effects. Our analysis focuses on how humans perceive automation technology when working within a process, allowing us to propose an effective engagement model between technology, process participants, process managers, and software developers. This paper offers insights and recommendations that can help organizations optimize their use of process automation. We further derive novel research questions for a discourse within the process automation community.

cs.SE↗

arXiv2024

Towards Nudging in BPM: A Human-Centric Approach for Sustainable Business Processes

Business Process Management (BPM) is mostly centered around finding technical solutions. Nudging is an approach from psychology and behavioral economics to guide people's behavior. In this paper, we show how nudging can be integrated into the different phases of the BPM lifecycle. Further, we outline how nudging can be an alternative strategy for more sustainable business processes. We show how the integration of nudging offers significant opportunities for process mining and business process management in general to be more human-centric. We also discuss challenges that come with the adoption of nudging.

cs.SE↗

arXiv2024

Unlocking Sustainability Compliance: Characterizing the EU Taxonomy for Business Process Management

To promote sustainable business practices, and to achieve climate neutrality by 2050, the EU has developed the taxonomy of sustainable activities, which describes when exactly business practices can be considered sustainable. While the taxonomy has only been recently established, progressively more companies will have to report how much of their revenue was created via sustainably executed business processes. To help companies prepare to assess whether their business processes comply with the constraints outlined in the taxonomy, we investigate in how far these criteria can be used for conformance checking, that is, assessing in a data-driven manner, whether business process executions adhere to regulatory constraints. For this, we develop a few-shot learning pipeline to characterize the constraints of the taxonomy with the help of an LLM as to the process dimensions they relate to. We find that many constraints of the taxonomy are useable for conformance checking, particularly in the sectors of energy, manufacturing, and transport. This will aid companies in preparing to monitor regulatory compliance with the taxonomy automatically, by characterizing what kind of information they need to extract, and by providing a better understanding of sectors where such an assessment is feasible and where it is not.

cs.CY↗

arXiv2024

Unraveling the Never-Ending Story of Lifecycles and Vitalizing Processes

Business process management (BPM) has been widely used to discover, model, analyze, and optimize organizational processes. BPM looks at these processes with analysis techniques that assume a clearly defined start and end. However, not all processes adhere to this logic, with the consequence that their behavior cannot be appropriately captured by BPM analysis techniques. This paper addresses this research problem at a conceptual level. More specifically, we introduce the notion of vitalizing business processes that target the lifecycle process of one or more entities. We show the existence of lifecycle processes in many industries and that their appropriate conceptualizations pave the way for the definition of suitable modeling and analysis techniques. This paper provides a set of requirements for their analysis, and a conceptualization of lifecycle and vitalizing processes.

cs.DB↗

arXiv2023

Timeline-based Process Discovery

A key concern of automatic process discovery is to provide insights into performance aspects of business processes. Waiting times are of particular importance in this context. For that reason, it is surprising that current techniques for automatic process discovery generate directly-follows graphs and comparable process models, but often miss the opportunity to explicitly represent the time axis. In this paper, we present an approach for automatically constructing process models that explicitly align with a time axis. We exemplify our approach for directly-follows graphs. Our evaluation using two BPIC datasets and a proprietary dataset highlight the benefits of this representation in comparison to standard layout techniques.

cs.HC↗

arXiv2023

Knowledge-Driven Modulation of Neural Networks with Attention Mechanism for Next Activity Prediction

Predictive Process Monitoring (PPM) aims at leveraging historic process execution data to predict how ongoing executions will continue up to their completion. In recent years, PPM techniques for the prediction of the next activities have matured significantly, mainly thanks to the use of Neural Networks (NNs) as a predictor. While their performance is difficult to beat in the general case, there are specific situations where background process knowledge can be helpful. Such knowledge can be leveraged for improving the quality of predictions for exceptional process executions or when the process changes due to a concept drift. In this paper, we present a Symbolic[Neuro] system that leverages background knowledge expressed in terms of a procedural process model to offset the under-sampling in the training data. More specifically, we make predictions using NNs with attention mechanism, an emerging technology in the NN field. The system has been tested on several real-life logs showing an improvement in the performance of the prediction task.

cs.AI↗

arXiv2023

Methodology of Algorithm Engineering

Research on algorithms has drastically increased in recent years. Various sub-disciplines of computer science investigate algorithms according to different objectives and standards. This plurality of the field has led to various methodological advances that have not yet been transferred to neighboring sub-disciplines. The central roadblock for a better knowledge exchange is the lack of a common methodological framework integrating the perspectives of these sub-disciplines. It is the objective of this paper to develop a research framework for algorithm engineering. Our framework builds on three areas discussed in the philosophy of science: ontology, epistemology and methodology. In essence, ontology describes algorithm engineering as being concerned with algorithmic problems, algorithmic tasks, algorithm designs and algorithm implementations. Epistemology describes the body of knowledge of algorithm engineering as a collection of prescriptive and descriptive knowledge, residing in World 3 of Popper's Three Worlds model. Methodology refers to the steps how we can systematically enhance our knowledge of specific algorithms. The framework helps us to identify and discuss various validity concerns relevant to any algorithm engineering contribution. In this way, our framework has important implications for researching algorithms in various areas of computer science.

cs.DS↗

arXiv2023

The Impact of Process Complexity on Process Performance: A Study using Event Log Data

Complexity is an important characteristic of any business process. The key assumption of much research in Business Process Management is that process complexity has a negative impact on process performance. So far, behavioral studies have measured complexity based on the perception of process stakeholders. The aim of this study is to investigate if such a connection can be supported based on the analysis of event log data. To do so, we employ a set of 38 metrics that capture different dimensions of process complexity. We use these metrics to build various regression models that explain process performance in terms of throughput time. We find that process complexity as captured in event logs explains the throughput time of process executions to a considerable extent, with the respective R-squared reaching up to 0.96. Our study offers implications for empirical research on process performance and can serve as a toolbox for practitioners.

cs.OH↗

arXiv2023

Large Language Models for Business Process Management: Opportunities and Challenges

Large language models are deep learning models with a large number of parameters. The models made noticeable progress on a large number of tasks, and as a consequence allowing them to serve as valuable and versatile tools for a diverse range of applications. Their capabilities also offer opportunities for business process management, however, these opportunities have not yet been systematically investigated. In this paper, we address this research problem by foregrounding various management tasks of the BPM lifecycle. We investigate six research directions highlighting problems that need to be addressed when using large language models, including usage guidelines for practitioners.

cs.SE↗

arXiv2022

Event-Case Correlation for Process Mining using Probabilistic Optimization

Process mining supports the analysis of the actual behavior and performance of business processes using event logs. % such as, e.g., sales transactions recorded by an ERP system. An essential requirement is that every event in the log must be associated with a unique case identifier (e.g., the order ID of an order-to-cash process). In reality, however, this case identifier may not always be present, especially when logs are acquired from different systems or extracted from non-process-aware information systems. In such settings, the event log needs to be pre-processed by grouping events into cases -- an operation known as event correlation. Existing techniques for correlating events have worked with assumptions to make the problem tractable: some assume the generative processes to be acyclic, while others require heuristic information or user input. Moreover, %these techniques' primary assumption is that they abstract the log to activities and timestamps, and miss the opportunity to use data attributes. % In this paper, we lift these assumptions and propose a new technique called EC-SA-Data based on probabilistic optimization. The technique takes as inputs a sequence of timestamped events (the log without case IDs), a process model describing the underlying business process, and constraints over the event attributes. Our approach returns an event log in which every event is associated with a case identifier. The technique allows users to incorporate rules on process knowledge and data constraints flexibly. The approach minimizes the misalignment between the generated log and the input process model, maximizes the support of the given data constraints over the correlated log, and the variance between activity durations across cases. Our experiments with various real-life datasets show the advantages of our approach over the state of the art.

cs.DB↗