arXiv subjects

Blaž Zupan

Publications and source records attributed to Blaž Zupan.

10 recordsLinked to original sources

arXiv2026

Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case Study

Biological literature retrieval systems are often developed and evaluated using broad biomedical corpora and general-purpose search tasks. However, many curated knowledge bases operate in narrower model-organism domains, where the literature is sparse and terminology is organism-specific. We introduce a retrieval benchmark from dictyBase for Dictyostelium, a model organism in cell and developmental biology. The benchmark consists of curator-generated biological queries linked to PubMed-indexed articles, together with structured gene annotations. Using this benchmark, we study three factors in niche biological retrieval: cross-encoder reranking, gene-aware query expansion, and abstract-only versus full-text retrieval. We report that reranking and gene-aware query expansion improve retrieval selectively: reranking is most useful when the model is well suited to biological evidence matching, whereas curated annotations help clarify compact biological queries by reducing vocabulary mismatch. Full-text chunks substantially improve retrieval when abstracts omit supporting evidence, increasing both candidate recall and top-rank performance, although these cases are harder than queries supported by abstracts. Data and code are publicly available at https://github.com/fulaibaowang/dictycite, and the benchmark dataset is additionally archived on Zenodo.

cs.IR↗

arXiv2026

Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning?

Biomedical relation extraction (BioRE) is a key step in transforming biomedical literature into structured knowledge. Most existing approaches rely on supervised models trained on costly annotated datasets, limiting their scalability and adaptability across relation types and domains. We investigate few-shot BioRE using prompt-based learning with large language models (LLMs) and compare two task formulations: pairwise classification, which predicts relations for individual entity pairs, and joint generation, which extracts multiple relations in a single model call. Experiments on the BioREDirect dataset reveal a clear precision-recall trade-off. Pairwise classification achieves higher recall, whereas joint generation is more precise and computationally efficient. The best-performing model achieves a micro-F1 score of 0.44, substantially outperforming previous few-shot results (0.34) while remaining below the supervised baseline (0.56). Much of this gap is attributable to a single ambiguously defined relation type. When evaluated using macro-F1, which better captures performance across relation types in an imbalanced setting, prompt-based approaches outperform the supervised baseline (0.45 vs. 0.38), particularly on rare relation types. These findings highlight the potential of LLMs for BioRE in low-resource settings and underscore the importance of well-defined relation schemas.

cs.CL↗

arXiv2026

Orange Lab: Lowering Barriers to Data Mining through Embedded Interactive Workflows

While visual programming of data analysis workflows has become an important vehicle for the democratization of data science, such systems remain largely confined to standalone applications and offer limited support for transitioning their visual analytics solutions into interactive web environments. As a result, data analysis pipelines are difficult to share, embed, and adapt into user-facing analytical tools. We present Orange Lab, a web-based collaborative environment for visual data analytics. At its core, Orange Lab enables users to visually construct machine learning workflows from modular components, where interactions in any component propagate seamlessly through the workflow, turning static pipelines into dynamic, reactive systems that support exploration and data-driven storytelling. Our key contribution is component exposition, a paradigm that allows authors to embed selected workflow components, or parts of their interfaces, into arbitrary web contexts, creating synchronized, interactive interfaces while hiding underlying workflow complexity. This enables the development of tailored analytical views and narrative-driven experiences that integrate data analysis directly into online materials. We demonstrate the approach through deployments in data literacy education, where embedded components guide students in hands-on exploration of machine learning concepts without requiring knowledge of the underlying system, showing that Orange Lab effectively lowers barriers to entry and supports the democratization of data science.

cs.LG↗

arXiv2026

Generating Statistical Charts with Validation-Driven LLM Workflows

Generating diverse, readable statistical charts from tabular data remains challenging for LLMs, as many failures become apparent after rendering and are not detectable from data or code alone. Existing chart datasets also rarely provide fully aligned artifacts, such as executable code, dataset context, and question-answer pairs. We present a structured LLM-based workflow that decomposes chart generation into dataset screening, plot proposal, code synthesis, rendering, validation-driven refinement, description generation, and question-answer generation. By incorporating rendered-output validation, the workflow addresses visualization-specific failure modes such as readability and semantic mismatch. It treats chart generation as an inspectable process rather than a one-shot prompt-to-code task, retaining each chart with its code, dataset context, description, and question-answer pairs. Applied to UCI datasets, the workflow produces 1,500 charts from 74 datasets, spanning 24 chart families and paired with 30,003 question-answer pairs. We evaluate 16 multimodal LLMs (MLLMs) on these chart-question pairs. The results show that chart-syntax questions are nearly saturated, while value extraction, comparison, and reasoning remain more challenging, illustrating the workflow's utility for diagnostic studies of chart-grounded multimodal reasoning.

cs.LG↗

arXiv2026

VERA: Generating Visual Explanations of Two-Dimensional Embeddings via Region Annotation

Two-dimensional embeddings obtained from dimensionality reduction techniques such as MDS, t-SNE, or UMAP, are widely used to visualize high-dimensional data and support researchers in visually identifying clusters, outliers, and other interesting patterns in the data. However, the main challenge is not only to detect such patterns, but to explain what they represent in terms of the original, human-interpretable features of the data. Existing approaches often rely on interactive exploration or direct feature encodings, requiring substantial manual inspection that can be time-consuming and repetitive. As an alternative, we propose VERA (Visual Explanations via Region Annotation), a general-purpose method for explaining two-dimensional embeddings through automatically generated, static, region-based visual explanations. VERA identifies informative regions in the embedding space and associates them with user-provided human-interpretable features, producing concise visual annotations that summarize the structure of the embedding landscape at a glance. Rather than merely showing where feature values occur, VERA automatically filters, merges, and ranks candidate explanations, enabling users to focus on the most informative embedding structures without manual exploration. We demonstrate VERA's utility on several real-world datasets and evaluate its effectiveness in a user study comparing it with the utility of a comprehensive interactive data mining toolkit. Our results show that VERA's generated static explanations can convey the essential insights of complex embeddings and support users in typical exploratory data analysis tasks, while requiring significantly less time and user effort.

cs.LG↗

arXiv2026

Inferring Chronic Treatment Onset from ePrescription Data: A Renewal Process Approach

Longitudinal electronic health record (EHR) data are often left-censored, making diagnosis records incomplete and unreliable for determining disease onset. In contrast, outpatient prescriptions form renewal-based trajectories that provide a continuous signal of disease management. We propose a probabilistic framework to infer chronic treatment onset by modeling prescription dynamics as a renewal process and detecting transitions from sporadic to sustained therapy via change-point detection between a baseline Poisson (sporadic prescribing) regime and a regime-specific Weibull (sustained therapy) renewal model. Using a nationwide ePrescription dataset of 2.4 million individuals, we show that the approach yields more temporally plausible onset estimates than naive rule-based triggering, substantially reducing implausible early detections under strong left censoring. Detection performance varies across diseases and is strongly associated with prescription density, highlighting both the strengths and limits of treatment-based onset inference.

cs.LG↗

arXiv2025

Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course

Providing students with individualized feedback through assignments is a cornerstone of education that supports their learning and development. Studies have shown that timely, high-quality feedback plays a critical role in improving learning outcomes. However, providing personalized feedback on a large scale in classes with large numbers of students is often impractical due to the significant time and effort required. Recent advances in natural language processing and large language models (LLMs) offer a promising solution by enabling the efficient delivery of personalized feedback. These technologies can reduce the workload of course staff while improving student satisfaction and learning outcomes. Their successful implementation, however, requires thorough evaluation and validation in real classrooms. We present the results of a practical evaluation of LLM-based graders for written assignments in the 2024/25 iteration of the Introduction to Bioinformatics course at the University of Ljubljana. Over the course of the semester, more than 100 students answered 36 text-based questions, most of which were automatically graded using LLMs. In a blind study, students received feedback from both LLMs and human teaching assistants without knowing the source, and later rated the quality of the feedback. We conducted a systematic evaluation of six commercial and open-source LLMs and compared their grading performance with human teaching assistants. Our results show that with well-designed prompts, LLMs can achieve grading accuracy and feedback quality comparable to human graders. Our results also suggest that open-source LLMs perform as well as commercial LLMs, allowing schools to implement their own grading systems while maintaining privacy.

cs.LG↗

arXiv2024

Uncovering Temporal Patterns in Visualizations of High-Dimensional Data

With the increasing availability of high-dimensional data, analysts often rely on exploratory data analysis to understand complex data sets. A key approach to exploring such data is dimensionality reduction, which embeds high-dimensional data in two dimensions to enable visual exploration. However, popular embedding techniques, such as t-SNE and UMAP, typically assume that data points are independent. When this assumption is violated, as in time-series data, the resulting visualizations may fail to reveal important temporal patterns and trends. To address this, we propose a formal extension to existing dimensionality reduction methods that incorporates two temporal loss terms that explicitly highlight temporal progression in the embedded visualizations. Through a series of experiments on both synthetic and real-world datasets, we demonstrate that our approach effectively uncovers temporal patterns and improves the interpretability of the visualizations. Furthermore, the method improves temporal coherence while preserving the fidelity of the embeddings, providing a robust tool for dynamic data analysis.

cs.LG↗

arXiv2021

Explainable Point-Based Document Visualizations

Two-dimensional data maps can visually reveal information about the relations between data instances. Popular techniques to construct data maps are t-SNE and UMAP. The resulting point-based visualizations, though, provide information only through their interpretation. We here consider a set of abstracts from the articles on longevity to argue for using keyword extraction methods to label clusters of documents in the map. Among the considered approaches, the best results were obtained by recently proposed YAKE!. Surprisingly, a classical TF-IDF term ranking outperformed graph and embedding-based techniques.

cs.IR↗

arXiv2015

Data Fusion by Matrix Factorization

For most problems in science and engineering we can obtain data sets that describe the observed system from various perspectives and record the behavior of its individual components. Heterogeneous data sets can be collectively mined by data fusion. Fusion can focus on a specific target relation and exploit directly associated data together with contextual data and data about system's constraints. In the paper we describe a data fusion approach with penalized matrix tri-factorization (DFMF) that simultaneously factorizes data matrices to reveal hidden associations. The approach can directly consider any data that can be expressed in a matrix, including those from feature-based representations, ontologies, associations and networks. We demonstrate the utility of DFMF for gene function prediction task with eleven different data sources and for prediction of pharmacologic actions by fusing six data sources. Our data fusion algorithm compares favorably to alternative data integration approaches and achieves higher accuracy than can be obtained from any single data source alone.

cs.LG↗