arXiv subjects

Max Unterbusch

Publications and source records attributed to Max Unterbusch.

7 recordsLinked to original sources

arXiv2026

On the Viability of Requirements Generation From Code: An Experience Report

Empirical research in Requirements Engineering is hampered by a lack of adequate datasets that pair source code with corresponding requirements. A tempting route to addressing this lack is the use of Large Language Models to synthesize requirements from existing code bases. We investigate this question by evaluating an LLM-based and RAG-supported agentic approach that generates requirements from source code, verifies their implementation status relying on a human-in-the-loop, and synthetically introduces requirements smells and non-implemented requirements. Our goal was to create datasets that mimic reality and foster empirical RE research. However, during the study, various problems arose, leading to this experience report. Contrary to our initial hypotheses, LLMs were unable to (i) generate non-implemented requirements reliably, (ii) generate high quality requirements, and (iii) reliably introduce synthetic requirements smells. Furthermore, neither an LLM nor a single human-in-the-loop suffices to detect requirements smells reliably. These findings suggest that the generation of code-to-requirements datasets using LLMs is not yet viable and requires human supervision, especially for quality assurance. We critically reflect on our lessons learned and draw relevant conclusions for both researchers and practitioners.

cs.SE↗

arXiv2026

V-SHiNE: A Virtual Smart Home Framework for Explainability Evaluation

Explanations are essential for helping users interpret and trust autonomous smart-home decisions, yet evaluating their quality and impact remains methodologically difficult in this domain. V-SHiNE addresses this gap: a browser-based smarthome simulation framework for scalable and realistic assessment of explanations. It allows researchers to configure environments, simulate behaviors, and plug in custom explanation engines, with flexible delivery modes and rich interaction logging. A study with 159 participants demonstrates its feasibility. V-SHiNE provides a lightweight, reproducible platform for advancing user-centered evaluation of explainable intelligent systems

cs.HC↗

arXiv2026

From Issues to Insights: RAG-based Explanation Generation from Software Engineering Artifacts

The increasing complexity of modern software systems has made understanding their behavior increasingly challenging, driving the need for explainability to improve transparency and user trust. Traditional documentation is often outdated or incomplete, making it difficult to derive accurate, context-specific explanations. Meanwhile, issue-tracking systems capture rich and continuously updated development knowledge, but their potential for explainability remains untapped. With this work, we are the first to apply a Retrieval-Augmented Generation (RAG) approach for generating explanations from issue-tracking data. Our proof-of-concept system is implemented using open-source tools and language models, demonstrating the feasibility of leveraging structured issue data for explanation generation. Evaluating our approach on an exemplary project's set of GitHub issues, we achieve 90% alignment with human-written explanations. Additionally, our system exhibits strong faithfulness and instruction adherence, ensuring reliable and grounded explanations. These findings suggest that RAG-based methods can extend explainability beyond black-box ML models to a broader range of software systems, provided that issue-tracking data is available - making system behavior more accessible and interpretable.

cs.SE↗

arXiv2026

Context-Adaptive Requirements Defect Prediction through Human-LLM Collaboration

Automated requirements assessment traditionally relies on universal patterns as proxies for defectiveness, implemented through rule-based heuristics or machine learning classifiers trained on large annotated datasets. However, what constitutes a "defect" is inherently context-dependent and varies across projects, domains, and stakeholder interpretations. In this paper, we propose a Human-LLM Collaboration (HLC) approach that treats defect prediction as an adaptive process rather than a static classification task. HLC leverages LLM Chain-of-Thought reasoning in a feedback loop: users validate predictions alongside their explanations, and these validated examples adaptively guide future predictions through few-shot learning. We evaluate this approach using the weak word smell on the QuRE benchmark of 1,266 annotated Mercedes-Benz requirements. Our results show that HLC effectively adapts to the provision of validated examples, with rapid performance gains from as few as 20 validated examples. Incorporating validated explanations, not just labels, enables HLC to substantially outperform both standard few-shot prompting and fine-tuned BERT models while maintaining high recall. These results highlight how the in-context and Chain-of-Thought learning capabilities of LLMs enable adaptive classification approaches that move beyond one-size-fits-all models, creating opportunities for tools that learn continuously from stakeholder feedback.

cs.SE↗

arXiv2025

Description and Comparative Analysis of QuRE: A New Industrial Requirements Quality Dataset

Requirements quality is central to successful software and systems engineering. Empirical research on quality defects in natural language requirements relies heavily on datasets, ideally as realistic and representative as possible. However, such datasets are often inaccessible, small, or lack sufficient detail. This paper introduces QuRE (Quality in Requirements), a new dataset comprising 2,111 industrial requirements that have been annotated through a real-world review process. Previously used for over five years as part of an industrial contract, this dataset is now being released to the research community. In this work, we furthermore provide descriptive statistics on the dataset, including measures such as lexical diversity and readability, and compare it to existing requirements datasets and synthetically generated requirements. In contrast to synthetic datasets, QuRE is linguistically similar to existing ones. However, this dataset comes with a detailed context description, and its labels have been created and used systematically and extensively in an industrial context over a period of close to a decade. Our goal is to foster transparency, comparability, and empirical rigor by supporting the development of a common gold standard for requirements quality datasets. This, in turn, will enable more sound and collaborative research efforts in the field.

cs.SE↗

arXiv2024

SmartEx: A Framework for Generating User-Centric Explanations in Smart Environments

Explainability is crucial for complex systems like pervasive smart environments, as they collect and analyze data from various sensors, follow multiple rules, and control different devices resulting in behavior that is not trivial and, thus, should be explained to the users. The current approaches, however, offer flat, static, and algorithm-focused explanations. User-centric explanations, on the other hand, consider the recipient and context, providing personalized and context-aware explanations. To address this gap, we propose an approach to incorporate user-centric explanations into smart environments. We introduce a conceptual model and a reference architecture for characterizing and generating such explanations. Our work is the first technical solution for generating context-aware and granular explanations in smart environments. Our architecture implementation demonstrates the feasibility of our approach through various scenarios.

cs.HC↗

arXiv2023

Explanation Needs in App Reviews: Taxonomy and Automated Detection

Explainability, i.e. the ability of a system to explain its behavior to users, has become an important quality of software-intensive systems. Recent work has focused on methods for generating explanations for various algorithmic paradigms (e.g., machine learning, self-adaptive systems). There is relatively little work on what situations and types of behavior should be explained. There is also a lack of support for eliciting explainability requirements. In this work, we explore the need for explanation expressed by users in app reviews. We manually coded a set of 1,730 app reviews from 8 apps and derived a taxonomy of Explanation Needs. We also explore several approaches to automatically identify Explanation Needs in app reviews. Our best classifier identifies Explanation Needs in 486 unseen reviews of 4 different apps with a weighted F-score of 86%. Our work contributes to a better understanding of users' Explanation Needs. Automated tools can help engineers focus on these needs and ultimately elicit valid Explanation Needs.

cs.SE↗