Sagar Sen

Dusica Marijan, Sagar Sen

Increasing the impact of software engineering research in the software industry and the society at large has long been a concern of high priority for the software engineering community. The problem of two cultures, research conducted in a vacuum (disconnected from the real world), or misaligned time horizons are just some of the many complex challenges standing in the way of successful industry-academia collaborations. This paper reports on the experience of research collaboration and knowledge co-creation between industry and academia in software engineering as a way to bridge the research-practice collaboration gap. Our experience spans 14 years of collaboration between researchers in software engineering and the European and Norwegian software and IT industry. Using the participant observation and interview methods we have collected and afterwards analyzed an extensive record of qualitative data. Drawing upon the findings made and the experience gained, we provide a set of 14 patterns and 14 anti-patterns for industry-academia collaborations, aimed to support other researchers and practitioners in establishing and running research collaboration projects in software engineering.

Erik Johannes Husom, Arda Goknil, Lwin Khin Shar et al.

In the rapidly evolving realm of artificial intelligence, deploying large language models (LLMs) poses increasingly pressing computational and environmental challenges. This paper introduces MELODI - Monitoring Energy Levels and Optimization for Data-driven Inference - a multifaceted framework crafted to monitor and analyze the energy consumed during LLM inference processes. MELODI enables detailed observations of power consumption dynamics and facilitates the creation of a comprehensive dataset reflective of energy efficiency across varied deployment scenarios. The dataset, generated using MELODI, encompasses a broad spectrum of LLM deployment frameworks, multiple language models, and extensive prompt datasets, enabling a comparative analysis of energy use. Using the dataset, we investigate how prompt attributes, including length and complexity, correlate with energy expenditure. Our findings indicate substantial disparities in energy efficiency, suggesting ample scope for optimization and adoption of sustainable measures in LLM deployment. Our contribution lies not only in the MELODI framework but also in the novel dataset, a resource that can be expanded by other researchers. Thus, MELODI is a foundational tool and dataset for advancing research into energy-conscious LLM deployment, steering the field toward a more sustainable future.

Erik Johannes Husom, Arda Goknil, Merve Astekin et al.

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to enable efficient LLM inference by reducing model size and computational overhead. In this study, we conduct a comprehensive analysis of 28 quantized LLMs from the Ollama library, which applies by default Post-Training Quantization (PTQ) and weight-only quantization techniques, deployed on an edge device (Raspberry Pi 4 with 4GB RAM). We evaluate energy efficiency, inference performance, and output accuracy across multiple quantization levels and task types. Models are benchmarked on five standardized datasets (CommonsenseQA, BIG-Bench Hard, TruthfulQA, GSM8K, and HumanEval), and we employ a high-resolution, hardware-based energy measurement tool to capture real-world power consumption. Our findings reveal the trade-offs between energy efficiency, inference speed, and accuracy in different quantization settings, highlighting configurations that optimize LLM deployment for resource-constrained environments. By integrating hardware-level energy profiling with LLM benchmarking, this study provides actionable insights for sustainable AI, bridging a critical gap in existing research on energy-aware LLM deployment.

Nicolas Jourdan, Sagar Sen, Erik Johannes Husom et al.

The increasing deployment of advanced digital technologies such as Internet of Things (IoT) devices and Cyber-Physical Systems (CPS) in industrial environments is enabling the productive use of machine learning (ML) algorithms in the manufacturing domain. As ML applications transcend from research to productive use in real-world industrial environments, the question of reliability arises. Since the majority of ML models are trained and evaluated on static datasets, continuous online monitoring of their performance is required to build reliable systems. Furthermore, concept and sensor drift can lead to degrading accuracy of the algorithm over time, thus compromising safety, acceptance and economics if undetected and not properly addressed. In this work, we exemplarily highlight the severity of the issue on a publicly available industrial dataset which was recorded over the course of 36 months and explain possible sources of drift. We assess the robustness of ML algorithms commonly used in manufacturing and show, that the accuracy strongly declines with increasing drift for all tested algorithms. We further investigate how uncertainty estimation may be leveraged for online performance estimation as well as drift detection as a first step towards continually learning applications. The results indicate, that ensemble algorithms like random forests show the least decay of confidence calibration under drift.

Mohit Kumar Ahuja, Mohamed-Bachir Belaid, Pierre Bernabé et al.

Trustworthiness is a central requirement for the acceptance and success of human-centered artificial intelligence (AI). To deem an AI system as trustworthy, it is crucial to assess its behaviour and characteristics against a gold standard of Trustworthy AI, consisting of guidelines, requirements, or only expectations. While AI systems are highly complex, their implementations are still based on software. The software engineering community has a long-established toolbox for the assessment of software systems, especially in the context of software testing. In this paper, we argue for the application of software engineering and testing practices for the assessment of trustworthy AI. We make the connection between the seven key requirements as defined by the European Commission's AI high-level expert group and established procedures from software engineering and raise questions for future work.

Stefan Wagner, Daniel Méndez Fernández, Michael Felderer et al.

Requirements Engineering (RE) has established itself as a software engineering discipline during the past decades. While researchers have been investigating the RE discipline with a plethora of empirical studies, attempts to systematically derive an empirically-based theory in context of the RE discipline have just recently been started. However, such a theory is needed if we are to define and motivate guidance in performing high quality RE research and practice. We aim at providing an empirical and valid foundation for a theory of RE, which helps software engineers establish effective and efficient RE processes. We designed a survey instrument and theory that has now been replicated in 10 countries world-wide. We evaluate the propositions of the theory with bootstrapped confidence intervals and derive potential explanations for the propositions. We report on the underlying theory and the full results obtained from the replication studies with participants from 228 organisations. Our results represent a substantial step forward towards developing an empirically-based theory of RE giving insights into current practices with RE processes. The results reveal, for example, that there are no strong differences between organisations in different countries and regions, that interviews, facilitated meetings and prototyping are the most used elicitation techniques, that requirements are often documented textually, that traces between requirements and code or design documents is common, requirements specifications themselves are rarely changed and that requirements engineering (process) improvement endeavours are mostly intrinsically motivated. Our study establishes a theory that can be used as starting point for many further studies for more detailed investigations. Practitioners can use the results as theory-supported guidance on selecting suitable RE methods and techniques.