arXiv subjects

Benjamin Paaßen

Publications and source records attributed to Benjamin Paaßen.

At least 19 recordsLinked to original sources

arXiv2026

Robust Deep Prototype Classifiers via Lipschitz Training

Robustness and interpretability are interrelated and desirable properties of machine learning models. A model that changes its prediction under imperceptible perturbations behaves inconsistently with human-recognizable features and, hence, is not interpretable. Prototype-based classifiers such as Generalized Learning Vector Quantization address both at once. They are interpretable by construction because they make the decision by comparing the input to the prototypical example; and their hypothesis margin yields a closed form robustness certificate. However, on high-dimensional data, these shallow models need deep embedding networks to achieve high accuracy, and this voids the robustness certificate. The margin is a statement about distances in the embedding space, and an unconstrained network can map an arbitrarily small input perturbation to arbitrarily large attacks in the embedding space. We close this gap with a theorem: if the embedding network is locally L-Lipschitz around a point, and the classifier is ε-robust around its embedding, then the full model is ε/L-robust in the input space. Based on this, we propose a Lipschitz training scheme to achieve L-Lipschitz properties for embedding networks. We evaluate three classification heads (linear, linear Support Vector Machine, and GLVQ) crossed with two embedding networks (standard and Lipschitz-constrained) on MNIST, CIFAR-10, and Imagenette-160, under FGS, PGD and C\&W attacks. The evaluation results show that combining a prototype-based head with a Lipschitz-constrained embedding provides the strongest robustness. This suggests that the Lipschitz constraint provides an additional robustness benefit in addition to the advantage provided by the prototype-based head. Since the Lipschitz constraint is enforced by sampling rather than by construction, the reported robustness is empirical rather than certified.

cs.LG↗

arXiv2026

Exploring the Limits of Large Language Models as a Reflection of Human Cognition: An Illustration in the Context of Moral Judgement

Large Language Models (LLMs), such as ChatGPT, are increasingly used in research, ranging from simple writing assistance to complex data annotation tasks. Recently, some research has suggested that LLMs are able to reproduce human responses to psychological questions and may, therefore, be used as simulators of human participants in some psychological research. We caution against this approach. Based on machine learning research, we argue that LLMs are likely to behave differently on novel stimuli compared to human study participants. We exemplify this in an experiment regarding moral judgments, demonstrating that slight changes to the wording of 30 moral scenarios used in prior work significantly reduce the similarity between ratings made by humans and LLMs, although the magnitude of this reduction varies across models. Therefore, we advise researchers to validate the similarity between human and LLM responses for their specific experiment.

cs.AI↗

arXiv2026

16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs

To deploy deep neural networks on edge hardware, highly efficient inference schemes are necessary that retain high accuracy. This work presents W16A16, a high precision (16-bit), fast speed, low energy quantization method. On a widely applied microcontroller architecture Armv7E-M, our proposed approach achieves faster speed and lower energy consumption on layer- and model-level compared to alternative quantization schemes. We analyze the architecture of Armv7E-M, explain the underlying principles behind the performance advantages of 16-bit approaches, and evaluate the empiric quantization errors for regression and classification tasks, as well as empiric time- and energy consumption in MCU deployment. We observe ca.\ 10 times lower quantization errors compared to 8-bit quantization schemes while achieving similar or better inference times and energy consumption.

cs.LG↗

arXiv2026

Limits of LLM Text Detectors in Education

Students increasingly use the assistance of large language models (LLMs) in their academic writing. While slight assistance (e.g., grammar and style correction, as well as feedback) is permitted under most institutional policies, it is usually forbidden to offload entire writing tasks to LLMs. Unfortunately, current approaches to LLM-generated text detection predominantly assume a binary distinction between human-written and LLM-generated text, ignoring the breadth of realistic human-AI collaboration practices and limiting the validity of detection systems for educational assessment. In this paper, we propose a contribution-aware evaluation framework for LLM-based detection systems in education. We introduce a scale of eight student contribution levels that model realistic writing scenarios ranging from fully human-written texts to LLM-assisted revisions to fully LLM-generated and adversarially humanized texts. Institutional policies regarding LLM use can then be translated to thresholds of acceptable LLM assistance on this scale. We further present Generative Essay Detection in Education (GEDE), a novel benchmark dataset comprising more than 900 human-written and over 12,500 generated essays across 886 tasks and all contribution levels. Using this benchmark, we conduct a systematic evaluation of four state-of-the-art zero-shot and supervised detection methods across policy boundaries, contribution levels, generative models, out-of-distribution data, and text length. We show that most detectors struggle to accurately classify texts at intermediate student contribution levels, in particular LLM-assisted revisions of human-written texts. Such errors pose a substantial risk of false accusations, indicating that current text detection systems are (still) unsuitable to reliably support the enforcement of institutional policies regarding LLM assistance in education.

cs.CL↗

arXiv2026

LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models

Large language model (LLM) research has grown rapidly, along with increasing concern about their limitations. In this survey, we conduct a data-driven, semi-automated review of research on limitations of LLMs (LLLMs) from 2022 to early 2025 using a bottom-up approach. From a corpus of 250,000 ACL and arXiv papers, we identify 14,648 relevant papers using keyword filtering, LLM-based classification, validated against expert labels, and topic clustering (via two approaches, HDBSCAN+BERTopic and LlooM). We find that the share of LLM-related papers increases over fivefold in ACL and nearly eightfold in arXiv between 2022 and 2025. Since 2022, LLLMs research grows even faster, reaching over 30% of LLM papers by 2025. Reasoning remains the most studied limitation, followed by generalization, hallucination, bias, and security. The distribution of topics in the ACL dataset stays relatively stable over time, while arXiv shifts toward security risks, alignment, hallucinations, knowledge editing, and multimodality. We offer a quantitative view of trends in LLLMs research and release a dataset of annotated abstracts and a validated methodology, available at: https://github.com/a-kostikova/LLLMs-Survey.

cs.CL↗

arXiv2025

Healthy Distrust in AI systems

Under the slogan of trustworthy AI, much of contemporary AI research is focused on designing AI systems and usage practices that inspire human trust and, thus, enhance adoption of AI systems. However, a person affected by an AI system may not be convinced by AI system design alone -- neither should they, if the AI system is embedded in a social context that gives good reason to believe that it is used in tension with a person's interest. In such cases, distrust in the system may be justified and necessary to build meaningful trust in the first place. We propose the term "healthy distrust" to describe such a justified, careful stance towards certain AI usage practices. We investigate prior notions of trust and distrust in computer science, sociology, history, psychology, and philosophy, outline a remaining gap that healthy distrust might fill and conceptualize healthy distrust as a crucial part for AI usage that respects human autonomy.

cs.CY↗

arXiv2024

Fairness in KI-Systemen

The more AI-assisted decisions affect people's lives, the more important the fairness of such decisions becomes. In this chapter, we provide an introduction to research on fairness in machine learning. We explain the main fairness definitions and strategies for achieving fairness using concrete examples and place fairness research in the European context. Our contribution is aimed at an interdisciplinary audience and therefore avoids mathematical formulation but emphasizes visualizations and examples. -- Je mehr KI-gestützte Entscheidungen das Leben von Menschen betreffen, desto wichtiger ist die Fairness solcher Entscheidungen. In diesem Kapitel geben wir eine Einführung in die Forschung zu Fairness im maschinellen Lernen. Wir erklären die wesentlichen Fairness-Definitionen und Strategien zur Erreichung von Fairness anhand konkreter Beispiele und ordnen die Fairness-Forschung in den europäischen Kontext ein. Unser Beitrag richtet sich dabei an ein interdisziplinäres Publikum und verzichtet daher auf die mathematische Formulierung sondern betont Visualisierungen und Beispiele.

cs.LG↗

arXiv2022

Automatic Creativity Measurement in Scratch Programs Across Modalities

Promoting creativity is considered an important goal of education, but creativity is notoriously hard to measure.In this paper, we make the journey fromdefining a formal measure of creativity that is efficientlycomputable to applying the measure in a practical domain. The measure is general and relies on coretheoretical concepts in creativity theory, namely fluency, flexibility, and originality, integratingwith prior cognitive science literature. We adapted the general measure for projects in the popular visual programming language Scratch.We designed a machine learning model for predicting the creativity of Scratch projects, trained and evaluated on human expert creativity assessments in an extensive user study. Our results show that opinions about creativity in Scratch varied widely across experts. The automatic creativity assessment aligned with the assessment of the human experts more than the experts agreed with each other. This is a first step in providing computational models for measuring creativity that can be applied to educational technologies, and to scale up the benefit of creativity education in schools.

cs.HC↗

arXiv2022

Revisiting the tree edit distance and its backtracing: A tutorial

Almost 30 years ago, Zhang and Shasha (1989) published a seminal paper describing an efficient dynamic programming algorithm computing the tree edit distance, that is, the minimum number of node deletions, insertions, and replacements that are necessary to transform one tree into another. Since then, the tree edit distance has been widely applied, for example in biology and intelligent tutoring systems. However, the original paper of Zhang and Shasha can be challenging to read for newcomers and it does not describe how to efficiently infer the optimal edit script. In this contribution, we provide a comprehensive tutorial to the tree edit distance algorithm of Zhang and Shasha. We further prove metric properties of the tree edit distance, and describe efficient algorithms to infer the cheapest edit script, as well as a summary of all cheapest edit scripts between two trees.

cs.DS↗

arXiv2021

An A*-algorithm for the Unordered Tree Edit Distance with Custom Costs

The unordered tree edit distance is a natural metric to compute distances between trees without intrinsic child order, such as representations of chemical molecules. While the unordered tree edit distance is MAX SNP-hard in principle, it is feasible for small cases, e.g. via an A* algorithm. Unfortunately, current heuristics for the A* algorithm assume unit costs for deletions, insertions, and replacements, which limits our ability to inject domain knowledge. In this paper, we present three novel heuristics for the A* algorithm that work with custom cost functions. In experiments on two chemical data sets, we show that custom costs make the A* computation faster and improve the error of a 5-nearest neighbor regressor, predicting chemical properties. We also show that, on these data, polynomial edit distances can achieve similar results as the unordered tree edit distance.

cs.AI↗

arXiv2021

Reservoir Stack Machines

Memory-augmented neural networks equip a recurrent neural network with an explicit memory to support tasks that require information storage without interference over long times. A key motivation for such research is to perform classic computation tasks, such as parsing. However, memory-augmented neural networks are notoriously hard to train, requiring many backpropagation epochs and a lot of data. In this paper, we introduce the reservoir stack machine, a model which can provably recognize all deterministic context-free languages and circumvents the training problem by training only the output layer of a recurrent net and employing auxiliary information during training about the desired interaction with a stack. In our experiments, we validate the reservoir stack machine against deep and shallow networks from the literature on three benchmark tasks for Neural Turing machines and six deterministic context-free languages. Our results show that the reservoir stack machine achieves zero error, even on test sequences longer than the training data, requiring only a few seconds of training time and 100 training sequences.

cs.NE↗

arXiv2021

Reservoir Memory Machines as Neural Computers

Differentiable neural computers extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks such as graph traversal. However, such models are difficult to train, requiring long training times and large datasets. In this work, we achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently, namely an echo state network with an explicit memory without interference. This extension enables echo state networks to recognize all regular languages, including those that contractive echo state networks provably can not recognize. Further, we demonstrate experimentally that our model performs comparably to its fully-trained deep version on several typical benchmark tasks for differentiable neural computers.

cs.LG↗

arXiv2021

ast2vec: Utilizing Recursive Neural Encodings of Python Programs

Educational datamining involves the application of datamining techniques to student activity. However, in the context of computer programming, many datamining techniques can not be applied because they expect vector-shaped input whereas computer programs have the form of syntax trees. In this paper, we present ast2vec, a neural network that maps Python syntax trees to vectors and back, thereby facilitating datamining on computer programs as well as the interpretation of datamining results. Ast2vec has been trained on almost half a million programs of novice programmers and is designed to be applied across learning tasks without re-training, meaning that users can apply it without any need for (additional) deep learning. We demonstrate the generality of ast2vec in three settings: First, we provide example analyses using ast2vec on a classroom-sized dataset, involving visualization, student motion analysis, clustering, and outlier detection, including two novel analyses, namely a progress-variance-projection and a dynamical systems analysis. Second, we consider the ability of ast2vec to recover the original syntax tree from its vector representation on the training data and two further large-scale programming datasets. Finally, we evaluate the predictive capability of a simple linear regression on top of ast2vec, obtaining similar results to techniques that work directly on syntax trees. We hope ast2vec can augment the educational datamining toolbelt by making analyses of computer programs easier, richer, and more efficient.

cs.LG↗

arXiv2019

Adversarial Edit Attacks for Tree Data

Many machine learning models can be attacked with adversarial examples, i.e. inputs close to correctly classified examples that are classified incorrectly. However, most research on adversarial attacks to date is limited to vectorial data, in particular image data. In this contribution, we extend the field by introducing adversarial edit attacks for tree-structured data with potential applications in medicine and automated program analysis. Our approach solely relies on the tree edit distance and a logarithmic number of black-box queries to the attacked classifier without any need for gradient information. We evaluate our approach on two programming and two biomedical data sets and show that many established tree classifiers, like tree-kernel-SVMs and recursive neural networks, can be attacked effectively.

cs.LG↗

arXiv2019

Embeddings and Representation Learning for Structured Data

Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Recent years have seen heightened attention in this demanding field of research and several new approaches have emerged, such as metric learning on structured data, graph convolutional neural networks, and recurrent decoder networks for structured data. In this contribution, we provide an high-level overview of the state-of-the-art in representation learning and embeddings for structured data across a wide range of machine learning fields.

cs.LG↗

arXiv2019

Dynamic fairness - Breaking vicious cycles in automatic decision making

In recent years, machine learning techniques have been increasingly applied in sensitive decision making processes, raising fairness concerns. Past research has shown that machine learning may reproduce and even exacerbate human bias due to biased training data or flawed model assumptions, and thus may lead to discriminatory actions. To counteract such biased models, researchers have proposed multiple mathematical definitions of fairness according to which classifiers can be optimized. However, it has also been shown that the outcomes generated by some fairness notions may be unsatisfactory. In this contribution, we add to this research by considering decision making processes in time. We establish a theoretic model in which even perfectly accurate classifiers which adhere to almost all common fairness definitions lead to stable long-term inequalities due to vicious cycles. Only demographic parity, which enforces equal rates of positive decisions across groups, avoids these effects and establishes a virtuous cycle, which leads to perfectly accurate and fair classification in the long term.

cs.LG↗

arXiv2018

Tree Edit Distance Learning via Adaptive Symbol Embeddings

Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart. Recent research has demonstrated that metric learning approaches can also be applied to trees, such as molecular structures, abstract syntax trees of computer programs, or syntax trees of natural language, by learning the cost function of an edit distance, i.e. the costs of replacing, deleting, or inserting nodes in a tree. However, learning such costs directly may yield an edit distance which violates metric axioms, is challenging to interpret, and may not generalize well. In this contribution, we propose a novel metric learning approach for trees which we call embedding edit distance learning (BEDL) and which learns an edit distance indirectly by embedding the tree nodes as vectors, such that the Euclidean distance between those vectors supports class discrimination. We learn such embeddings by reducing the distance to prototypical trees from the same class and increasing the distance to prototypical trees from different classes. In our experiments, we show that BEDL improves upon the state-of-the-art in metric learning for trees on six benchmark data sets, ranging from computer science over biomedical data to a natural-language processing data set containing over 300,000 nodes.

cs.LG↗

arXiv2018

The Continuous Hint Factory - Providing Hints in Vast and Sparsely Populated Edit Distance Spaces

Intelligent tutoring systems can support students in solving multi-step tasks by providing hints regarding what to do next. However, engineering such next-step hints manually or via an expert model becomes infeasible if the space of possible states is too large. Therefore, several approaches have emerged to infer next-step hints automatically, relying on past students' data. In particular, the Hint Factory (Barnes & Stamper, 2008) recommends edits that are most likely to guide students from their current state towards a correct solution, based on what successful students in the past have done in the same situation. Still, the Hint Factory relies on student data being available for any state a student might visit while solving the task, which is not the case for some learning tasks, such as open-ended programming tasks. In this contribution we provide a mathematical framework for edit-based hint policies and, based on this theory, propose a novel hint policy to provide edit hints in vast and sparsely populated state spaces. In particular, we extend the Hint Factory by considering data of past students in all states which are similar to the student's current state and creating hints approximating the weighted average of all these reference states. Because the space of possible weighted averages is continuous, we call this approach the Continuous Hint Factory. In our experimental evaluation, we demonstrate that the Continuous Hint Factory can predict more accurately what capable students would do compared to existing prediction schemes on two learning tasks, especially in an open-ended programming task, and that the Continuous Hint Factory is comparable to existing hint policies at reproducing tutor hints on a simple UML diagram task.

cs.AI↗