Related papers: Determining Context Factors for Hybrid Development…
Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…
Creativity has become a core competence in the era of LLMs and human-AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment…
This paper studies how global dynamics and knowledge of high-level features can inform decision-making for robots in flow-like environments. Specifically, we investigate how coherent sets, an environmental feature found in these…
[Context and Motivation]: The quality of requirements specifications impacts subsequent, dependent software engineering activities. Requirements quality defects like ambiguous statements can result in incomplete or wrong features and even…
Modeling environmental ecosystems is essential for effective resource management, sustainable development, and understanding complex ecological processes. However, traditional data-driven methods face challenges in capturing inherently…
When evaluating the efficacy of social programs and medical treatments using randomized experiments, the estimated overall average causal effect alone is often of limited value and the researchers must investigate when the treatments do and…
Context sensitivity is essential for achieving the precision in inter-procedural static analysis. To be (fully) context sensitive, top-down analysis needs to fully inline all statements of the callees at each callsite, leading to statement…
Software development, despite all the significant improvements it contributes to society, is a very expensive high-risk venture. Every software project commences with the intention to deliver a software product on time and within budget,…
Research shows that many of the challenges currently encountered with agile development are related to requirements engineering. Based on design science research, this paper investigates critical challenges that arise in agile development…
Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy search offers data-efficient learning and generalization by…
Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation…
Faithful evaluation of language model capabilities is crucial for deriving actionable insights that can inform model development. However, rigorous causal evaluations in this domain face significant methodological challenges, including…
Many planning and decision activities in logistics and supply chain management are based on forecasts of multiple time dependent factors. Therefore, the quality of planning depends on the quality of the forecasts. We compare various…
Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for…
This paper presents a framework that guides the requirements engineer in the implementation and execution of an effective requirements generation process. We achieve this goal by providing a well-defined requirements engineering model and a…
The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…
The first step in constructing a machine learning model is defining the features of the data set that can be used for optimal learning. In this work we discuss feature selection methods, which can be used to build better models, as well as…
Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the…
Analysing and improving productivity has been one of the main goals of software engineering research since its beginnings. A plethora of studies has been conducted on various factors that resulted in several models for analysis and…
Gathering training data is a key step of any supervised learning task, and it is both critical and expensive. Critical, because the quantity and quality of the training data has a high impact on the performance of the learned function.…