Matthieu Brinkhuis

Diana Kolesnikova, Kirill Fedyanin, Abe D. Hofman et al.

Accurate estimates of item difficulty are essential for valid assessment and effective adaptive learning. However, for newly created tasks, response data are typically unavailable. Pretesting and expert judgement can be costly and slow, while machine learning methods often require large labelled training datasets. Recent work suggests that large language models (LLMs) may help. However, there is limited evidence on the elicitation procedures and prompt configurations used to emulate experts for difficulty estimation. This study addresses this gap by evaluating three off-the-shelf LLMs as difficulty raters for newly created items without access to response data. Using an item bank from an online learning system, the study examined 6 domains of primary-school mathematics, with empirical difficulty estimates treated as empirical reference. The study used a full factorial design crossing three factors: judgement format (absolute vs pairwise), decision type (hard decisions vs token-probability-based estimates), and prompting strategy (zero-shot vs few-shot). LLM-derived difficulty estimates were compared with empirical difficulties using Spearman rank correlations. Across domains, LLM-based estimates exhibited moderate to strong positive correlations with empirical item difficulties. For simpler arithmetic tasks, some configurations approached the upper end of the accuracy range reported for human experts in previous research. Pairwise comparison consistently outperformed absolute judgement in the absence of additional refinements. However, when token-level probabilities were incorporated and examples of items with known empirical difficulty were provided, the absolute judgement configuration likewise demonstrated moderate-to-high alignment. The study positions LLMs as a promising tool for initial item calibration and offers insights into effective workflow configuration.

Jan Martijn E. M. van der Werf, Artem Polyvyanyy, Bart R. van Wensveen et al.

The aim of a process discovery algorithm is to construct from event data a process model that describes the underlying, real-world process well. Intuitively, the better the quality of the event data, the better the quality of the model that is discovered. However, existing process discovery algorithms do not guarantee this relationship. We demonstrate this by using a range of quality measures for both event data and discovered process models. This paper is a call to the community of IS engineers to complement their process discovery algorithms with properties that relate qualities of their inputs to those of their outputs. To this end, we distinguish four incremental stages for the development of such algorithms, along with concrete guidelines for the formulation of relevant properties and experimental validation. We will also use these stages to reflect on the state of the art, which shows the need to move forward in our thinking about algorithmic process discovery.

Jasper van der Waa, Marcel Robeer, Jurriaan van Diggelen et al.

Recent advances in interpretable Machine Learning (iML) and eXplainable AI (XAI) construct explanations based on the importance of features in classification tasks. However, in a high-dimensional feature space this approach may become unfeasible without restraining the set of important features. We propose to utilize the human tendency to ask questions like "Why this output (the fact) instead of that output (the foil)?" to reduce the number of features to those that play a main role in the asked contrast. Our proposed method utilizes locally trained one-versus-all decision trees to identify the disjoint set of rules that causes the tree to classify data points as the foil and not as the fact. In this study we illustrate this approach on three benchmark classification tasks.