Abstract Multi-task learning (MTL) enables a single neural network to solve multiple tasks simultaneously, offering efficiency and improved generalization potential through shared representations. A central challenge in MTL is balancing task-specific losses during training to avoid performance degradation. While uncertainty-based loss weighting (UW) is a popular and competitive approach, we argue that it suffers from several limitations, including overfitting, rigid homoscedastic assumptions, and a lack of theoretical grounding for various loss functions. Therefore, we propose Soft Optimal Uncertainty Weighting (UW-SO), a novel loss weighting method that builds on UW by deriving analytically optimal weights and applying softmax normalization with adaptable temperature parameter, thereby alleviating several of the shortcomings of UW. Through extensive experiments across diverse datasets and architectures, we show that UW-SO achieves superior and robust performance compared to a variety of existing loss weighting methods. Additionally, we provide insights into the effects of temperature selection and propose measures to reduce computational demand.

Figure 1: GUI prototype (1) and three views (2-4) of our assistant for GUI prototype designers integrated as a plug-in into a prototyping tool.Our assistant displays user stories (2) imported from collaboration tools (e.g., JIRA) for prototype designers to reference while working.It detects whether a user story is implemented (3, 4), identifies relevant GUI components (3), and generates GUI components for user stories (4). Figure uses Google Material 3 Design Kit [24] components under CC BY 4.0.

Exploration is a crucial skill for in-context reinforcement learning in unknown environments. However, it remains unclear if large language models can effectively explore a partially hidden state space. This work isolates exploration as the sole objective, tasking an agent with gathering information that enhances future returns. Within this framework, we argue that measuring agent returns is not sufficient for a fair evaluation. Hence, we decompose missing rewards into their exploration and exploitation components based on the optimal achievable return. Experiments with various models reveal that most struggle to explore the state space, and weak exploration is insufficient. Nevertheless, we found a positive correlation between exploration performance and reasoning capabilities. Our decomposition can provide insights into differences in behaviors driven by prompt engineering, offering a valuable tool for refining performance in exploratory tasks.

LIME (Local Interpretable Model-agnostic Explanations) is a well-known XAI framework for unraveling decision-making processes in vision machine-learning models. The technique utilizes image segmentation methods to identify fixed regions for calculating feature importance scores as explanations. Therefore, poor segmentation can weaken the explanation and reduce the importance of segments, ultimately affecting the overall clarity of interpretation. To address these challenges, we introduce the DSEG-LIME (Data-Driven Segmentation LIME) framework, featuring: i) a data-driven segmentation for human-recognized feature generation by foundation model integration, and ii) a user-steered granularity in the hierarchical segmentation procedure through composition. Our findings demonstrate that DSEG outperforms on several XAI metrics on pretrained ImageNet models and improves the alignment of explanations with human-recognized concepts.

Reinforcement learning (RL) has seen significant success across various domains, but its adoption is often limited by the black-box nature of neural network policies, making them difficult to interpret. In contrast, symbolic policies allow representing decision-making strategies in a compact and interpretable way. However, learning symbolic policies directly within on-policy methods remains challenging. In this paper, we introduce SYMPOL, a novel method for SYMbolic tree-based on-POLicy RL. SYMPOL employs a tree-based model integrated with a policy gradient method, enabling the agent to learn and adapt its actions while maintaining a high level of interpretability. We evaluate SYMPOL on a set of benchmark RL tasks, demonstrating its superiority over alternative tree-based RL approaches in terms of performance and interpretability. Unlike existing methods, it enables gradient-based, end-to-end learning of interpretable, axis-aligned decision trees within standard on-policy RL algorithms. Therefore, SYMPOL can become the foundation for a new class of interpretable RL based on decision trees. Our implementation is available under: https://github.com/s-marton/sympol

Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Data-efficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concepts across different granularities. Exclusively containing dataset-specific concepts, DCBMs are well suited for fine-grained classification and out-of-distribution tasks. Attribution analysis using Grad-CAM demonstrates that DCBMs deliver visual concepts that can be localized in test images. By leveraging dataset-specific concepts instead of predefined or general ones, DCBMs enhance adaptability to new domains. The code is available at: https://github.com/KathPra/DCBM.

Graphical User Interface (GUI) prototyping is a fundamental component in the development of modern interactive systems, which are now ubiquitous across diverse application domains. GUI prototypes play a critical role in requirements elicitation by enabling stakeholders to visualize, assess, and refine system concepts collaboratively. Moreover, prototypes serve as effective tools for early testing, iterative evaluation, and validation of design ideas with both end users and development teams. Despite these advantages, the process of constructing GUI prototypes remains resource-intensive and time-consuming, frequently demanding substantial effort and expertise. Recent research has sought to alleviate this burden through natural language (NL)-based GUI retrieval approaches, which typically rely on embedding-based retrieval or tailored ranking models for specific GUI repositories. However, these methods often suffer from limited retrieval performance and struggle to generalize across arbitrary GUI datasets. In this work, we present GUI-ReRank, a novel framework that integrates rapid embedding-based constrained retrieval models with highly effective multi-modal (M)LLM-based reranking techniques. GUI-ReRank further introduces a fully customizable GUI repository annotation and embedding pipeline, enabling users to effortlessly make their own GUI repositories searchable, which allows for rapid discovery of relevant GUIs for inspiration or seamless integration into customized LLM-based retrieval-augmented generation (RAG) workflows. We evaluated our approach on an established NL-based GUI retrieval benchmark, demonstrating that GUI-ReRank significantly outperforms state-of-the-art (SOTA) tailored Learning-to-Rank (LTR) models in both retrieval accuracy and generalizability. Additionally, we conducted a comprehensive cost and efficiency analysis of employing MLLMs for reranking, providing valuable insights regarding the trade-offs between retrieval effectiveness and computational resources. Video presentation of GUI-ReRank available at: https://youtu.be/7x9UCh82ug

Jannik Brinkmann, Chris Wendler, Christian Bartelt, Aaron Mueller. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability. However, learning a DT from data is a difficult optimization problem, as it is non-convex and non-differentiable. Therefore, common approaches learn DTs using a greedy growth algorithm that minimizes the impurity locally at each internal node. Unfortunately, this greedy procedure can lead to inaccurate trees. In this paper, we present a novel approach for learning hard, axis-aligned DTs with gradient descent. The proposed method uses backpropagation with a straight-through operator on a dense DT representation, to jointly optimize all tree parameters. Our approach outperforms existing methods on binary classification benchmarks and achieves competitive results for multi-class tasks. The implementation is available under: https://github.com/s-marton/GradTree

We present a new approach to goal recognition that involves comparing observed facts with their expected probabilities. These probabilities depend on a specified goal g and initial state s0. Our method maps these probabilities and observed facts into a real vector space to compute heuristic values for potential goals. These heuristic values estimate the likelihood of a given goal being the true objective of the observed agent. As obtaining exact expected probabilities for observed facts in an observation sequence is often practically infeasible, we propose and empirically validate a method for approximating these probabilities. Our empirical results show that the proposed approach offers improved goal recognition precision compared to state-of-the-art techniques while reducing computational complexity.

Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, there is a significant need for tabular-specific gradient-based methods due to their high flexibility. In this paper, we propose $\text{GRANDE}$, $\text{GRA}$die$\text{N}$t-Based $\text{D}$ecision Tree $\text{E}$nsembles, a novel approach for learning hard, axis-aligned decision tree ensembles using end-to-end gradient descent. GRANDE is based on a dense representation of tree ensembles, which affords to use backpropagation with a straight-through operator to jointly optimize all model parameters. Our method combines axis-aligned splits, which is a useful inductive bias for tabular data, with the flexibility of gradient-based optimization. Furthermore, we introduce an advanced instance-wise weighting that facilitates learning representations for both, simple and complex relations, within a single model. We conducted an extensive evaluation on a predefined benchmark with 19 classification datasets and demonstrate that our method outperforms existing gradient-boosting and deep learning frameworks on most datasets. The method is available under: https://github.com/s-marton/GRANDE

Requirements Elicitation (RE) is a crucial activity especially in the early stages of software development. GUI prototyping has widely been adopted as one of the most effective RE techniques for user-facing software systems. However, GUI prototyping requires (i) the availability of experienced requirements analysts, (ii) typically necessitates conducting multiple joint sessions with customers and (iii) creates considerable manual effort. In this work, we propose SERGUI, a novel approach enabling the Self-Elicitation of Requirements (SER) based on an automated GUI prototyping assistant. SERGUI exploits the vast prototyping knowledge embodied in a large-scale GUI repository through Natural Language Requirements (NLR) based GUI retrieval and facilitates fast feedback through GUI prototypes. The GUI retrieval approach is closely integrated with a Large Language Model (LLM) driving the prompting-based recommendation of GUI features for the current GUI prototyping context and thus stimulating the elicitation of additional requirements. We envision SERGUI to be employed in the initial RE phase, creating an initial GUI prototype specification to be used by the analyst as a means for communicating the requirements. To measure the effectiveness of our approach, we conducted a preliminary evaluation. Video presentation of SERGUI at: https://youtu.be/pzAAB9Uht80

Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing performance differences typically have model-centered evaluation setups with overly standardized data preprocessing. This limits the external validity of these studies, as in real-world modeling pipelines, models are typically applied after dataset-specific preprocessing and feature engineering. We address this gap by proposing a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. We conduct experiments with different preprocessing pipelines and hyperparameter optimization (HPO) regimes to quantify the impact of model selection, HPO, feature engineering, and test-time adaptation. Our main findings reveal: 1) After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces. 2) Recent models, despite their measurable progress, still significantly benefit from manual feature engineering. This holds true for both tree-based models and neural networks. 3) While tabular data is typically considered static, samples are often collected over time, and adapting to distribution shifts can be important even in supposedly static data. These insights suggest that research efforts should be directed toward a data-centric perspective, acknowledging that tabular data requires feature engineering and often exhibits temporal characteristics.

Interactive systems are omnipresent today and the need to create graphical user interfaces (GUIs) is just as ubiq-uitous. For the elicitation and validation of requirements, GUI prototyping is a well-known and effective technique, typically employed after gathering initial user requirements represented in natural language (NL) (e.g., in the form of user stories). Un-fortunately, G UI prototyping often requires extensive resources, resulting in a costly and time-consuming process. Despite various easy-to-use prototyping tools in practice, there is often a lack of adequate resources for developing G UI prototypes based on given user requirements. In this work, we present a novel Large Language Model (LLM)-based approach providing assistance for validating the implementation of functional NL- based require-ments in a GUI prototype embedded in a prototyping tool. In particular, our approach aims to detect functional user stories that are not implemented in a G UI prototype and provides recommendations for suitable GUI components directly imple-menting the requirements. We collected requirements for existing GUIs in the form of user stories and evaluated our proposed validation and recommendation approach with this dataset. The obtained results are promising for user story validation and we demonstrate feasibility for the GUI component recommendations.

Abstract We consider generating explanations for neural networks in cases where the network’s training data is not accessible, for instance due to privacy or safety issues. Recently, Interpretation Nets ( $$\mathcal {I}$$ I -Nets) have been proposed as a sample-free approach to post-hoc, global model interpretability that does not require access to training data. They formulate interpretation as a machine learning task that maps network representations (parameters) to a representation of an interpretable function. In this paper, we extend the $$\mathcal {I}$$ I -Net framework to the cases of standard and soft decision trees as surrogate models. We propose a suitable decision tree representation and design of the corresponding $$\mathcal {I}$$ I -Net output layers. Furthermore, we make $$\mathcal {I}$$ I -Nets applicable to real-world tasks by considering more realistic distributions when generating the $$\mathcal {I}$$ I -Net’s training data. We empirically evaluate our approach against traditional global, post-hoc interpretability approaches and show that it achieves superior results when the training data is not accessible.

In this paper, we propose a new online learning algorithm tailored for data streams described by varying feature spaces (VFS), wherein new features constantly emerge and old features may stop to be observed over various time spans. Our proposed algorithm, named Online Random Feature Forests for Feature space Variabilities (ORF3V), provides a strategy to respect such feature dynamics by generating, updating, pruning, as well as online re-weighing an ensemble of what we call feature forests, which are generated and updated based on a compressed and storage efficient representation for each observed feature. We benchmark our algorithm on 12 datasets, including one novel real-world dataset of government COVID-19 responses collected through a crowd-sensing program in Spain. The empirical results substantiate the viability and effectiveness of our ORF3V algorithm and its superior accuracy performance over the state-of-the-art rival models.

The embedding spaces of image models have been shown to encode a range of social biases such as racism and sexism. Here, we investigate specific factors that contribute to the emergence of these biases in Vision Transformers (ViT). Therefore, we measure the impact of training data, model architecture, and training objectives on social biases in the learned representations of ViTs. Our findings indicate that counterfactual augmentation training using diffusion-based image editing can mitigate biases, but does not eliminate them. Moreover, we find that larger models are less biased than smaller models, and that models trained using discriminative objectives are less biased than those trained using generative objectives. In addition, we observe inconsistencies in the learned social biases. To our surprise, ViTs can exhibit opposite biases when trained on the same data set using different self-supervised objectives. Our findings give insights into the factors that contribute to the emergence of social biases and suggests that we could achieve substantial fairness improvements based on model design choices.

Abstract Rapid GUI prototyping has evolved into a widely applied technique in early stages of software development to facilitate the clarification and refinement of requirements. Especially high-fidelity GUI prototyping has shown to enable productive discussions with customers and mitigate potential misunderstandings, however, the benefits of applying high-fidelity GUI prototypes are accompanied by the disadvantage of being expensive and time-consuming in development and requiring experience to create. In this work, we showRaWi, a data-driven GUI prototyping approach that effectively retrieves GUIs for reuse from a large-scale semi-automatically created GUI repository for mobile apps on the basis of Natural Language (NL) searches to facilitate GUI prototyping and improve its productivity by leveraging the vast GUI prototyping knowledge embodied in the repository. Retrieved GUIs can directly be reused and adapted in the graphical editor ofRaWi. Moreover, we present a comprehensive evaluation methodology to enable (i) the systematic evaluation of NL-based GUI ranking methods through a novel high-quality gold standard and conduct an in-depth evaluation of traditional IR and state-of-the-art BERT-based models for GUI ranking, and (ii) the assessment of GUI prototyping productivity accompanied by an extensive user study in a practical GUI prototyping environment.

Sum-Product Networks (SPNs) are expressive probabilistic models that provide exact, tractable inference. They achieve this efficiency by making use of local independence. On the other hand, mixtures of exchangeable variable models (MEVMs) are a class of tractable probabilistic models that make use of exchangeability of discrete random variables to render inference tractable. Exchangeability, which arises naturally in relational domains, has not been considered for efficient representation and inference in SPNs yet. The contribution of this paper is a novel probabilistic model which we call Exchangeability-Aware Sum-Product Networks (XSPNs). It contains both SPNs and MEVMs as special cases, and combines the ability of SPNs to efficiently learn deep probabilistic models with the ability of MEVMs to efficiently handle exchangeable random variables. We introduce a structure learning algorithm for XSPNs and empirically show that they can be more accurate than conventional SPNs when the data contains repeated, interchangeable parts.

High-fidelity Graphical User Interface (GUI) prototyping is a well-established and suitable method for enabling fruitful discussions, clarification and refinement of requirements formulated by customers. GUI prototypes can help to reduce misunderstandings between customers and developers, which may occur due to the ambiguity comprised in informal Natural Language (NL). However, a disadvantage of employing high-fidelity GUI prototypes is their time-consuming and expensive development. Common GUI prototyping tools are based on combining individual GUI components or manually crafted templates. In this work, we present GUI2WiRe, a tool that enables users to retrieve GUI prototypes from a semiautomatically created large-scale GUI repository for mobile applications matching user requirements specified in Natural Language (NLR). We extract multiple text segments from the GUI hierarchy data and employ various Information Retrieval (IR) models and Automatic Query Expansion (AQE) techniques to achieve ad-hoc GUI retrieval from NLR. Retrieved GUI prototypes mined from applications can be inserted in the graphical editor of GUI2WiRe to rapidly create wireframes. GUI components are extracted automatically from the GUI screenshots and basic editing functionality is provided to the user. Finally, a preview of the application is created from the wireframe to allow interactive exploration of the current design. We evaluated the applied IR and AQE approaches for their effectiveness in terms of GUI retrieval relevance on a manually annotated collection of NLR and discuss our planned user studies. Video presentation of GUI2WiRe: https://youtu.be/2nN-Xr2Hk7I

Component models for IoT devices regain popularity. As more and more devices must be semantically connected within IoT platforms, digital abstractions for these devices are needed. For this purpose, textual device descriptions which encapsulate device-specific characteristics are a suitable candidate. Such component descriptions formally describe a device's information model as well as the offered functionality in a standardized way. However, smart IoT platforms mainly solve user goals by composing various IoT devices in a suitable manner. Current IoT descriptions, such as Eclipse Vorto do not address this need at all. In this paper, we introduce a formal mapping language that allows to capture functional interaction semantics already during device integration time. Our evaluation shows that only few mapping elements are needed to define functional mappings between operations as well as to capture the underlying communication pattern.

Global software engineering has become a fact in many companies due to real necessity in practice. In contrast to co-located projects global projects face a number of additional software engineering challenges. Among them quality management has become much more difficult and schedule and budget overruns can be observed more often. Compared to co-located projects global software engineering is even more challenging due to the need for integration of different cultures, different languages, and different time zones-across companies, and across countries. The diversity of development locations on several levels seriously endangers an effective and goal-oriented progress of projects. In this position paper we discuss reasons for global development, sketch settings for distribution and views of orchestration of dislocated companies in a global project that can be seen as a ldquovirtual project environmentrdquo. We also present a collection of questions, which we consider relevant for global software engineering. The questions motivate further discussion to derive a research agenda in global software engineering.