arXiv subjects

Anna Wróblewska

Publications and source records attributed to Anna Wróblewska.

At least 19 recordsLinked to original sources

arXiv2026

ClickGuard: Detecting and Spoiling Clickbait News with Informativeness Measures and Large Language Models

This paper presents an AI-driven browser extension that identifies clickbait to help users avoid misleading Internet articles. Moving beyond traditional detection, the application employs a hybrid machine learning architecture that combines transformer-based embeddings with linguistically motivated features and a custom "baitness" score. After evaluating various natural language processing techniques -- from classic vectorizers to large language model (LLM) embeddings -- an XGBoost-based model was developed that achieves an F1-score of 91% on the open combined dataset. Most importantly, the tool can warn users before and after they access a clickbait article. After opening an article, the user receives a percentage score indicating the likelihood that it is clickbait. The prediction is explained based on the analyzed metrics, including those specifically developed within the proposed system. The browser extension also provides a clickbait spoiler -- a one- to two-sentence summary of the entire article. Demo video:https://www.youtube.com/watch?v=IJ1gkQV82C4}{https://www.youtube.com/watch?v=IJ1gkQV82C4

cs.AI↗

arXiv2026

From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle

This demo paper describes the development of the AI Teaching \& Learning Assistant, a modular Moodle plugin that leverages Retrieval-Augmented Generation (RAG) to deliver high-quality, hallucination-free education. The system employs a dual-centric design, providing students with interactive, Socratic-based tutoring and educators with a "human-in-the-loop" workspace for supervised content generation. By grounding Large Language Model (LLM) responses in teacher-provided materials, the assistant addresses the risks of misinformation while encouraging deep conceptual mastery. Evaluation via the Ragas (LLM-as-a-Judge) framework and a preliminary user study confirms its effectiveness, achieving faithfulness scores up to 0.97 and a 4.00/5.00 recommendation rate.

cs.HC↗

arXiv2026

Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs

The rapid spread of online misinformation has led to increasingly complex detection models, including large language models and hybrid architectures. However, their computational cost and deployment limitations raise concerns about practical applicability. In this work, we benchmark graph neural networks (GNNs) against non-graph-based machine learning methods under controlled and comparable conditions. We evaluate lightweight GNN architectures (GCN, GraphSAGE, GAT, ChebNet) against Logistic Regression, Support Vector Machines, and Multilayer Perceptrons across seven public datasets in English, Indonesian, and Polish. All models use identical TF-IDF features to isolate the impact of relational structure. Performance is measured using F1 score, with inference time reported to assess efficiency. GNNs consistently outperform non-graph baselines across all datasets. For example, GraphSAGE achieves 96.8% F1 on Kaggle and 91.9% on WELFake, compared to 73.2% and 66.8% for MLP, respectively. On COVID-19, GraphSAGE reaches 90.5% F1 vs. 74.9%, while ChebNet attains 79.1% vs. 66.4% on FakeNewsNet. These gains are achieved with comparable or lower inference times. Overall, the results show that classic GNNs remain effective and efficient, challenging the need for increasingly complex architectures in misinformation detection.

cs.CL↗

arXiv2026

Clickbait detection: quick inference with maximum impact

We propose a lightweight hybrid approach to clickbait detection that combines OpenAI semantic embeddings with six compact heuristic features capturing stylistic and informational cues. To improve efficiency, embeddings are reduced using PCA and evaluated with XGBoost, GraphSAGE, and GCN classifiers. While the simplified feature design yields slightly lower F1-scores, graph-based models achieve competitive performance with substantially reduced inference time. High ROC--AUC values further indicate strong discrimination capability, supporting reliable detection of clickbait headlines under varying decision thresholds.

cs.CL↗

arXiv2026

LLM Essay Scoring Under Holistic and Analytic Rubrics: Prompt Effects and Bias

Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open essay-scoring datasets (ASAP 2.0, ELLIPSE, and DREsS) that cover both holistic and analytic scoring. We analyze agreement with human consensus scores, directional bias, and the stability of bias estimates. Our results show that strong open-weight models achieve moderate to high agreement with humans on holistic scoring (Quadratic Weighted Kappa about 0.6), but this does not transfer uniformly to analytic scoring. In particular, we observe large and stable negative directional bias on Lower-Order Concern (LOC) traits, such as Grammar and Conventions, meaning that models often score these traits more harshly than human raters. We also find that concise keyword-based prompts generally outperform longer rubric-style prompts in multi-trait analytic scoring. To quantify the amount of data needed to detect these systematic deviations, we compute the minimum sample size at which a 95% bootstrap confidence interval for the mean bias excludes zero. This analysis shows that LOC bias is often detectable with very small validation sets, whereas Higher-Order Concern (HOC) traits typically require much larger samples. These findings support a bias-correction-first deployment strategy: instead of relying on raw zero-shot scores, systematic score offsets can be estimated and corrected using small human-labeled bias-estimation sets, without requiring large-scale fine-tuning.

cs.CL↗

arXiv2026

On the Effectiveness of LLM-Specific Fine-Tuning for Detecting AI-Generated Text

The rapid progress of large language models has enabled the generation of text that closely resembles human writing, creating challenges for authenticity verification in education, publishing, and digital security. Detecting AI-generated text has therefore become a crucial technical and ethical issue. This paper presents a comprehensive study of AI-generated text detection based on large-scale corpora and novel training strategies. We introduce a 1-billion-token corpus of human-authored texts spanning multiple genres and a 1.9-billion-token corpus of AI-generated texts produced by prompting a variety of LLMs across diverse domains. Using these resources, we develop and evaluate numerous detection models and propose two novel training paradigms: Per LLM and Per LLM family fine-tuning. Across a 100-million-token benchmark covering 21 large language models, our best fine-tuned detector achieves up to $99.6\%$ token-level accuracy, substantially outperforming existing open-source baselines.

cs.CL↗

arXiv2025

How to Make Museums More Interactive? Case Study of Artistic Chatbot

Conversational agents powered by Large Language Models (LLMs) are increasingly utilized in educational settings, in particular in individual closed digital environments, yet their potential adoption in the physical learning environments like cultural heritage sites, museums, and art galleries remains relatively unexplored. In this study, we present Artistic Chatbot, a voice-to-voice RAG-powered chat system to support informal learning and enhance visitor engagement during a live art exhibition celebrating the 15th anniversary of the Faculty of Media Art at the Warsaw Academy of Fine Arts, Poland. The question answering (QA) chatbot responded to free-form spoken questions in Polish using the context retrieved from a curated, domain-specific knowledge base consisting of 226 documents provided by the organizers, including faculty information, art magazines, books, and journals. We describe the key aspects of the system architecture and user interaction design, as well as discuss the practical challenges associated with deploying chatbots at public cultural sites. Our findings, based on interaction analysis, demonstrate that chatbots such as Artistic Chatbot effectively maintain responses grounded in exhibition content (60\% of responses directly relevant), even when faced with unpredictable queries outside the target domain, showing their potential for increasing interactivity in public cultural sites. GitHub project page: https://github.com/cinekucia/artistic-chatbot-cikm2025

cs.HC↗

arXiv2025

Evaluating LLM-Generated Q&A Test: a Student-Centered Study

This research prepares an automatic pipeline for generating reliable question-answer (Q&A) tests using AI chatbots. We automatically generated a GPT-4o-mini-based Q&A test for a Natural Language Processing course and evaluated its psychometric and perceived-quality metrics with students and experts. A mixed-format IRT analysis showed that the generated items exhibit strong discrimination and appropriate difficulty, while student and expert star ratings reflect high overall quality. A uniform DIF check identified two items for review. These findings demonstrate that LLM-generated assessments can match human-authored tests in psychometric performance and user satisfaction, illustrating a scalable approach to AI-assisted assessment development.

cs.CL↗

arXiv2025

Fake News Detection: It's All in the Data!

This comprehensive survey serves as an indispensable resource for researchers embarking on the journey of fake news detection. By highlighting the pivotal role of dataset quality and diversity, it underscores the significance of these elements in the effectiveness and robustness of detection models. The survey meticulously outlines the key features of datasets, various labeling systems employed, and prevalent biases that can impact model performance. Additionally, it addresses critical ethical issues and best practices, offering a thorough overview of the current state of available datasets. Our contribution to this field is further enriched by the provision of GitHub repository, which consolidates publicly accessible datasets into a single, user-friendly portal. This repository is designed to facilitate and stimulate further research and development efforts aimed at combating the pervasive issue of fake news.

cs.CL↗

arXiv2025

Applying Text Mining to Analyze Human Question Asking in Creativity Research

Creativity relates to the ability to generate novel and effective ideas in the areas of interest. How are such creative ideas generated? One possible mechanism that supports creative ideation and is gaining increased empirical attention is by asking questions. Question asking is a likely cognitive mechanism that allows defining problems, facilitating creative problem solving. However, much is unknown about the exact role of questions in creativity. This work presents an attempt to apply text mining methods to measure the cognitive potential of questions, taking into account, among others, (a) question type, (b) question complexity, and (c) the content of the answer. This contribution summarizes the history of question mining as a part of creativity research, along with the natural language processing methods deemed useful or helpful in the study. In addition, a novel approach is proposed, implemented, and applied to five datasets. The experimental results obtained are comprehensively analyzed, suggesting that natural language processing has a role to play in creative research.

cs.CL↗

arXiv2024

Consumer Transactions Simulation through Generative Adversarial Networks

In the rapidly evolving domain of large-scale retail data systems, envisioning and simulating future consumer transactions has become a crucial area of interest. It offers significant potential to fortify demand forecasting and fine-tune inventory management. This paper presents an innovative application of Generative Adversarial Networks (GANs) to generate synthetic retail transaction data, specifically focusing on a novel system architecture that combines consumer behavior modeling with stock-keeping unit (SKU) availability constraints to address real-world assortment optimization challenges. We diverge from conventional methodologies by integrating SKU data into our GAN architecture and using more sophisticated embedding methods (e.g., hyper-graphs). This design choice enables our system to generate not only simulated consumer purchase behaviors but also reflects the dynamic interplay between consumer behavior and SKU availability -- an aspect often overlooked, among others, because of data scarcity in legacy retail simulation models. Our GAN model generates transactions under stock constraints, pioneering a resourceful experimental system with practical implications for real-world retail operation and strategy. Preliminary results demonstrate enhanced realism in simulated transactions measured by comparing generated items with real ones using methods employed earlier in related studies. This underscores the potential for more accurate predictive modeling.

cs.LG↗

arXiv2024

Intelligent Interface: Enhancing Lecture Engagement with Didactic Activity Summaries

Recently, multiple applications of machine learning have been introduced. They include various possibilities arising when image analysis methods are applied to, broadly understood, video streams. In this context, a novel tool, developed for academic educators to enhance the teaching process by automating, summarizing, and offering prompt feedback on conducting lectures, has been developed. The implemented prototype utilizes machine learning-based techniques to recognise selected didactic and behavioural teachers' features within lecture video recordings. Specifically, users (teachers) can upload their lecture videos, which are preprocessed and analysed using machine learning models. Next, users can view summaries of recognized didactic features through interactive charts and tables. Additionally, stored ML-based prediction results support comparisons between lectures based on their didactic content. In the developed application text-based models trained on lecture transcriptions, with enhancements to the transcription quality, by adopting an automatic speech recognition solution are applied. Furthermore, the system offers flexibility for (future) integration of new/additional machine-learning models and software modules for image and video analysis.

cs.AI↗

arXiv2024

Mining United Nations General Assembly Debates

This project explores the application of Natural Language Processing (NLP) techniques to analyse United Nations General Assembly (UNGA) speeches. Using NLP allows for the efficient processing and analysis of large volumes of textual data, enabling the extraction of semantic patterns, sentiment analysis, and topic modelling. Our goal is to deliver a comprehensive dataset and a tool (interface with descriptive statistics and automatically extracted topics) from which political scientists can derive insights into international relations and have the opportunity to have a nuanced understanding of global diplomatic discourse.

cs.CL↗

arXiv2024

Improving Object Detection Quality in Football Through Super-Resolution Techniques

This study explores the potential of super-resolution techniques in enhancing object detection accuracy in football. Given the sport's fast-paced nature and the critical importance of precise object (e.g. ball, player) tracking for both analysis and broadcasting, super-resolution could offer significant improvements. We investigate how advanced image processing through super-resolution impacts the accuracy and reliability of object detection algorithms in processing football match footage. Our methodology involved applying state-of-the-art super-resolution techniques to a diverse set of football match videos from SoccerNet, followed by object detection using Faster R-CNN. The performance of these algorithms, both with and without super-resolution enhancement, was rigorously evaluated in terms of detection accuracy. The results indicate a marked improvement in object detection accuracy when super-resolution preprocessing is applied. The improvement of object detection through the integration of super-resolution techniques yields significant benefits, especially for low-resolution scenarios, with a notable 12\% increase in mean Average Precision (mAP) at an IoU (Intersection over Union) range of 0.50:0.95 for 320x240 size images when increasing the resolution fourfold using RLFN. As the dimensions increase, the magnitude of improvement becomes more subdued; however, a discernible improvement in the quality of detection is consistently evident. Additionally, we discuss the implications of these findings for real-time sports analytics, player tracking, and the overall viewing experience. The study contributes to the growing field of sports technology by demonstrating the practical benefits and limitations of integrating super-resolution techniques in football analytics and broadcasting.

cs.CV↗

arXiv2023

Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives

Action scene understanding in soccer is a challenging task due to the complex and dynamic nature of the game, as well as the interactions between players. This article provides a comprehensive overview of this task divided into action recognition, spotting, and spatio-temporal action localization, with a particular emphasis on the modalities used and multimodal methods. We explore the publicly available data sources and metrics used to evaluate models' performance. The article reviews recent state-of-the-art methods that leverage deep learning techniques and traditional methods. We focus on multimodal methods, which integrate information from multiple sources, such as video and audio data, and also those that represent one source in various ways. The advantages and limitations of methods are discussed, along with their potential for improving the accuracy and robustness of models. Finally, the article highlights some of the open research questions and future directions in the field of soccer action recognition, including the potential for multimodal methods to advance this field. Overall, this survey provides a valuable resource for researchers interested in the field of action scene understanding in soccer.

cs.CV↗

arXiv2023

Automating the Analysis of Institutional Design in International Agreements

This paper explores the automatic knowledge extraction of formal institutional design - norms, rules, and actors - from international agreements. The focus was to analyze the relationship between the visibility and centrality of actors in the formal institutional design in regulating critical aspects of cultural heritage relations. The developed tool utilizes techniques such as collecting legal documents, annotating them with Institutional Grammar, and using graph analysis to explore the formal institutional design. The system was tested against the 2003 UNESCO Convention for the Safeguarding of the Intangible Cultural Heritage.

cs.CL↗

arXiv2023

Enriching language models with graph-based context information to better understand textual data

A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets relate via users that follow each other or reshare content. Hence, a graph-like structure can represent existing connections and be seen as capturing the "context" of the texts. The question thus arises if extracting and integrating such context information into a language model might help facilitate a better automated understanding of the text. In this study, we experimentally demonstrate that incorporating graph-based contextualization into BERT model enhances its performance on an example of a classification task. Specifically, on Pubmed dataset, we observed a reduction in error from 8.51% to 7.96%, while increasing the number of parameters just by 1.6%. Our source code: https://github.com/tryptofanik/gc-bert

cs.CL↗

arXiv2022

Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning

This paper presents an analysis regarding an influence of the Distance Metric Learning (DML) loss functions on the supervised fine-tuning of the language models for classification tasks. We experimented with known datasets from SentEval Transfer Tasks. Our experiments show that applying the DML loss function can increase performance on downstream classification tasks of RoBERTa-large models in few-shot scenarios. Models fine-tuned with the use of SoftTriple loss can achieve better results than models with a standard categorical cross-entropy loss function by about 2.89 percentage points from 0.04 to 13.48 percentage points depending on the training dataset. Additionally, we accomplished a comprehensive analysis with explainability techniques to assess the models' reliability and explain their results.

cs.CL↗