In recent years, we can observe a trend of creating various specific language models (LMs) within the Slavic language family with the Bert architecture. However, with an increasing number of parameters of LM, a larger amount of text is required for good performance, which can hinder the development and creation of LMs for specific languages. Our research is looking for a solution in Curriculum learning(CL) methods that can help us build better models with a lower amount of text in comparison with current LMs, which can help in better prtraining of models with low resource languages(LRL). Therefore, we replicate the BabyLM Challenge in the Slovak language (Dataset: https://huggingface.co/datasets/ubokri/SlovakBabyLM, Code: https://github.com/baucek/Slovakbabylm/tree/main). Additionally, apply CL to test and see the difference in the application of CL methods on the English and Slovak languages and evaluate whether the CL improves performance of LM. Our experiments show that the use of CL methods as preprocessing methods is significant for improving model performance in sentiment analysis and question answering.

This study explores the task of automatically extracting migration-related locations (source and destination) from media articles, focusing on the challenges posed by Slovak, a low-resource and morphologically complex language. We present the first comparative analysis of rule-based dictionary approaches (NLP4SK) versus Large Language Models (LLMs, e.g. SlovakBERT, GPT-4o) for both geographical relevance classification (Slovakia-focused migration) and specific source/target location extraction. To facilitate this research and future work, we introduce the first manually annotated Slovak dataset tailored for migration-focused locality detection. Our results show that while a fine-tuned SlovakBERT model achieves high accuracy for classification, specialized rule-based methods still have the potential to outperform LLMs for specific extraction tasks, though improved LLM performance with few-shot examples suggests future competitiveness as research in this area continues to evolve.

Large Language Models (LLMs) have significantly altered the landscape of Natural Language Processing (NLP), having topped the benchmarks of many standard tasks and problems, particularly when used in combination with Retrieval Augmented Generation (RAG). Despite their impressive performance and relative simplicity, its use as a baseline method has not been extensive. One of the reasons might be that adapting and optimizing RAG-based pipelines for specific NLP tasks generally requires custom development which is difficult to scale. In this work we introduce RAGthoven, a tool for automatic evaluation of RAG-based pipelines. It provides a simple yet powerful abstraction, which allows the user to start the evaluation process with nothing more than a single configuration file. To demonstrate its usefulness we conduct three case studies spanning text classification, question answering and code generation usecases. We release the code, as well as the documentation and tutorials, at https://github.com/ragthoven-dev/ragthoven

Large language models show promising performance on reasoning tasks, yet evaluation methods for low-resource languages remain limited, particularly for complex STEM problem-solving. We introduce Trojsten Benchmark, a Slovak-language dataset of 1,108 high-school competition problems with reference solutions across mathematics, physics, and programming, and a rubric-based LLM grading framework. Using GPT-4 to generate rubrics and grade solutions, we observe 1.05 average absolute deviation from human graders (5-point scale), while benchmarking GPT-3.5-Turbo, GPT-4, GPT-4o, and open-weight models (Llama 3, Phi-3). We quantify multistep reasoning performance by difficulty, show consistent underperformance on harder items, and demonstrate language sensitivity: accuracy drops on English translations of Slovak statements, evidencing challenges beyond translation. Trojsten Benchmark complements English-centric math datasets (e.g., MATH, GSM8K) by targeting open-response, rubric-gradable reasoning under low-resource linguistic framing. We release code and data to enable reproducible evaluation and human-aligned auto-grading for STEM in under-served languages.

In this work, we introduce skLEP, the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding (NLU) models. We have compiled skLEP to encompass nine diverse tasks that span token-level, sentence-pair, and document-level challenges, thereby offering a thorough assessment of model capabilities. To create this benchmark, we curated new, original datasets tailored for Slovak and meticulously translated established English NLU resources. Within this paper, we also present the first systematic and extensive evaluation of a wide array of Slovak-specific, multilingual, and English pre-trained language models using the skLEP tasks. Finally, we also release the complete benchmark data, an open-source toolkit facilitating both fine-tuning and evaluation of models, and a public leaderboard at https://github.com/slovak-nlp/sklep in the hopes of fostering reproducibility and drive future research in Slovak NLU.

This paper presents a system for SemEval 2025 Task 2 on entity-aware machine translation, integrating GPT-4o with Wikidata-based translations, retrieval augmented generation (RAG), and function calling. Implemented in RAGthoven, a lightweight yet powerful toolkit, our approach enriches source sentences with real-time external knowledge to address challenging or culturally specific named entities. Experiments on English-to-ten target languages show notable gains in translation quality, illustrating how LLM-based translation pipelines can leverage knowledge sources with minimal overhead. Its simplicity makes it a strong baseline for future research in entity-focused machine translation.

This study details our approach for the CASE 2024 Shared Task on Climate Activism Stance and Hate Event Detection, focusing on Hate Speech Detection, Hate Speech Target Identification, and Stance Detection as classification challenges. We explored the capability of Large Language Models (LLMs), particularly GPT-4, in zero- or few-shot settings enhanced by retrieval augmentation and re-ranking for Tweet classification. Our goal was to determine if LLMs could match or surpass traditional methods in this context. We conducted an ablation study with LLaMA for comparison, and our results indicate that our models significantly outperformed the baselines, securing second place in the Target Detection task. The code for our submission is available at https://github.com/NaiveNeuron/bryndza-case-2024

Large Language Models (LLMs) are increasingly influential in Computational Social Science, offering new methods for processing and analyzing data, particularly in lower-resource language contexts. This study explores the use of OpenAI’s GPT-3.5 Turbo and GPT-4 for automating annotations for a unique news media dataset in a lower resourced language, focusing on stance classification tasks. Our results reveal that prompting in the native language, explanation generation, and advanced prompting strategies like Retrieval Augmented Generation and Chain of Thought prompting enhance LLM performance, particularly noting GPT-4’s superiority in predicting stance. Further evaluation indicates that LLMs can serve as a useful tool for social science text annotation in lower resourced languages, notably in identifying inconsistencies in annotation guidelines and annotated datasets.

The ability to automatically summarize news articles has become increasingly important due to the vast amount of information available online. Together with the rise of chatbots , Natural Language Processing (NLP) has recently experienced a tremendous amount of development. Despite these advancements, the majority of research is focused on established well-resourced languages, such as English. To contribute to development of the low resource Slovak language, we introduce SlovakSum, a Slovak news summarization dataset consisting of over 200 thousand news articles with titles and short abstracts obtained from multiple Slovak newspapers. The abstractive approach, including MBART and mT5 models, was used to evaluate various baselines. The code for the reproduction of our dataset and experiments can be found at https://github.com/NaiveNeuron/slovaksum

We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages. The overarching goal of UNER is to provide high-quality, cross-lingually consistent annotations to facilitate and standardize multilingual NER research. UNER v1 contains 19 datasets annotated with named entities in a cross-lingual consistent schema across 13 diverse languages. In this paper, we detail the dataset creation and composition of UNER; we also provide initial modeling baselines on both in-language and cross-lingual learning settings. We will release the data, code, and fitted models to the public.

While Large Language Models (LLMs) have demonstrated considerable potential in advancing natural language processing in dialect-specific contexts, their effectiveness in these settings has yet to be thoroughly assessed. This study introduces a case study on Šariš, a dialect of Slovak, which is itself a language with fewer resources, focusing on Machine Translation and Common Sense Reasoning tasks. We employ LLMs in a zero-shot configuration and for data augmentation to refine Slovak-Šariš and Šariš-Slovak translation models. The accuracy of these models is then manually verified by native speakers. Additionally, we introduce ŠarišCOPA, a new dataset for causal common sense reasoning, which, alongside SlovakCOPA, serves to evaluate LLM’s performance in a zero-shot framework. Our findings highlight LLM’s capabilities in processing low-resource dialects and suggest a viable approach for initiating dialect-specific translation models in such contexts.

Named Entity Recognition (NER) is a fundamental NLP tasks with a wide range of practical applications. The performance of state-of-the-art NER methods depends on high quality manually anotated datasets which still do not exist for some languages. In this work we aim to remedy this situation in Slovak by introducing WikiGoldSK, the first sizable human labelled Slovak NER dataset. We benchmark it by evaluating state-of-the-art multilingual Pretrained Language Models and comparing it to the existing silver-standard Slovak NER dataset. We also conduct few-shot experiments and show that training on a sliver-standard dataset yields better results. To enable future work that can be based on Slovak NER, we release the dataset, code, as well as the trained models publicly under permissible licensing terms at https://github.com/NaiveNeuron/WikiGoldSK

With the advent of Large Language Models (LLMs) the process known as prompting, which entices the LLM to solve an arbitrary language processing task without the need for finetuning, has risen to prominence. Finding well-performing prompts, however, is a non-trivial task which requires experimentation in order to arrive at a prompt that solves a specific task. When a given task does not readily reduce to one that can be easily measured with well established metrics, human evaluation of the results obtained by prompting is often necessary. In this work we present prompterator, a tool that helps the user interactively iterate over various potential prompts and choose the best performing one based on human feedback. It is distributed as an open source package with out-of-the-box support for various LLM providers and was designed to be easily extensible.

In this paper we describe TraSpaS, a submission to the third shared task on named entity recognition hosted as part of the Balto-Slavic Natural Language Processing (BSNLP) Workshop. In it we evaluate various pre-trained language models on the NER task using three open-source NLP toolkits: character level language model with Stanza, language-specific BERT-style models with SpaCy and Adapter-enabled XLM-R with Trankit. Our results show that the Trankit-based models outperformed those based on the other two toolkits, even when trained on smaller amounts of data. Our code is available at https://github.com/NaiveNeuron/slavner-2021.

In this study, we demonstrate the viability of deploying BERT-style models to AWS Lambda in a production environment. Since the freely available pre-trained models are too large to be deployed in this environment, we utilize knowledge distillation and fine-tune the models on proprietary datasets for two real-world tasks: sentiment analysis and semantic textual similarity. As a result, we obtain models that are tuned for a specific domain and deployable in the serverless environment. The subsequent performance analysis shows that this solution does not only report latency levels acceptable for production use but that it is also a cost-effective alternative to small-to-medium size deployments of BERT models, all without any infrastructure overhead.

As a well established NLP task, single-document summarization has seen significant interest in the past few years. However, most of the work has been done on English datasets. This is particularly noticeable in the context of evaluation where the dominant ROUGE metric assumes its input to be written in English. In this paper we aim to address both of these issues by introducing a summarization dataset of articles from a popular Slovak news site and proposing small adaptation to the ROUGE metric that make it better suited for Slovak texts. Several baselines are evaluated on the dataset, including an extractive approach based on the Multilingual version of the BERT architecture. To the best of our knowledge, the presented dataset is the first large-scale news-based summarization dataset for text written in Slovak language. It can be reproduced using the utilities available at https://github.com/NaiveNeuron/sme-sum