We present Irish-BLiMP (Irish Benchmark of Linguistic Minimal Pairs), the first dataset and framework designed for fine-grained evaluation of linguistic competence in the Irish language, an endangered language. Drawing on a variety of linguistic literature and grammar reference works, we manually constructed and reviewed 1020 minimal pairs across a taxonomy of 11 linguistic features, through a team of fluent Irish speakers. We evaluate both existing Large Language Models (LLMs) and fluent human participants on their syntactic knowledge of Irish. Our findings show that humans outperform all models across all linguistic features, achieving 16.6% higher accuracy on average. Moreover, a substantial performance gap of 18.1% persists between open- and closed-source LLMs, with even the strongest model (gpt-5) reaching only 73.5% accuracy compared to 90.1% by human. Interestingly, human participants and models struggle on different aspects of Irish grammar, thus highlighting a difference in representation learned by the models. Overall, Irish-BLiMP provides the first systematic framework for evaluating the grammatical competence of LLMs in Irish and offers a valuable benchmark for advancin
Large language model (LLM) research and development has overwhelmingly focused on the world's major languages, leading to under-representation of low-resource languages such as Irish. This paper introduces \textbf{Qomhrá}, a bilingual Irish and English LLM, developed under extremely low-resource constraints. A complete pipeline is outlined spanning bilingual continued pre-training, instruction tuning, and the synthesis of human preference data for future alignment training. We focus on the lack of scalable methods to create human preference data by proposing a novel method to synthesise such data by prompting an LLM to generate ``accepted'' and ``rejected'' responses, which we validate as aligning with L1 Irish speakers. To select an LLM for synthesis, we evaluate the top closed-weight LLMs for Irish language generation performance. Gemini-2.5-Pro is ranked highest by L1 and L2 Irish-speakers, diverging from LLM-as-a-judge ratings, indicating a misalignment between current LLMs and the Irish-language community. Subsequently, we leverage Gemini-2.5-Pro to translate a large scale English-language instruction tuning dataset to Irish and to synthesise a first-of-its-kind Irish-language
The development of Large Language Models (LLMs) has predominantly focused on high-resource languages, leaving extremely low-resource languages like Irish with limited representation. This work presents UCCIX, a pioneering effort on the development of an open-source Irish-based LLM. We propose a novel framework for continued pre-training of LLMs specifically adapted for extremely low-resource languages, requiring only a fraction of the textual data typically needed for training LLMs according to scaling laws. Our model, based on Llama 2-13B, outperforms much larger models on Irish language tasks with up to 12% performance improvement, showcasing the effectiveness and efficiency of our approach. We also contribute comprehensive Irish benchmarking datasets, including IrishQA, a question-answering dataset, and Irish version of MT-bench. These datasets enable rigorous evaluation and facilitate future research in Irish LLM systems. Our work aims to preserve and promote the Irish language, knowledge, and culture of Ireland in the digital era while providing a framework for adapting LLMs to other indigenous languages.
Existing multilingual benchmarks include Irish among dozens of languages but apply no Irish-aware text normalisation, leaving reliable and reproducible ASR comparison impossible. We introduce BlasBench, an open evaluation harness that provides a standalone Irish-aware normaliser preserving fadas, lenition, and eclipsis; a reproducible scoring harness and per-utterance predictions released for all evaluated runs. We pilot this by benchmarking 12 systems across four architecture families on Common Voice ga-IE and FLEURS ga-IE. All Whisper variants exceed 100% WER through insertion-driven hallucination. Microsoft Azure reaches 22.2% WER on Common Voice and 57.5% on FLEURS; the best open model, Omnilingual ASR 7B, reaches 30.65% and 39.09% respectively. Models fine-tuned on Common Voice degrade 33-43 points moving to FLEURS, while massively multilingual models degrade only 7-10 - a generalisation gap that single-dataset evaluation misses.
Recent advances in Large Language Models (LLMs) have demonstrated promising knowledge and reasoning abilities, yet their performance in multilingual and low-resource settings remains underexplored. Existing benchmarks often exhibit cultural bias, restrict evaluation to text-only, rely on multiple-choice formats, and, more importantly, are limited for extremely low-resource languages. To address these gaps, we introduce IRLBench, presented in parallel English and Irish, which is considered definitely endangered by UNESCO. Our benchmark consists of 12 representative subjects developed from the 2024 Irish Leaving Certificate exams, enabling fine-grained analysis of model capabilities across domains. By framing the task as long-form generation and leveraging the official marking scheme, it does not only support a comprehensive evaluation of correctness but also language fidelity. Our extensive experiments of leading closed-source and open-source LLMs reveal a persistent performance gap between English and Irish, in which models produce valid Irish responses less than 80\% of the time, and answer correctly 55.8\% of the time compared to 76.2\% in English for the best-performing model. W
This study examines hallucinations in Large Language Model (LLM) translations into Irish, specifically focusing on instances where the models generate novel, non-existent words. We classify these hallucinations within verb and noun categories, identifying six distinct patterns among the latter. Additionally, we analyse whether these hallucinations adhere to Irish morphological rules and what linguistic tendencies they exhibit. Our findings show that while both GPT-4.o and GPT-4.o Mini produce similar types of hallucinations, the Mini model generates them at a significantly higher frequency. Beyond classification, the discussion raises speculative questions about the implications of these hallucinations for the Irish language. Rather than seeking definitive answers, we offer food for thought regarding the increasing use of LLMs and their potential role in shaping Irish vocabulary and linguistic evolution. We aim to prompt discussion on how such technologies might influence language over time, particularly in the context of low-resource, morphologically rich languages.
The Richards equation (RE) is widely used to model water flow in unsaturated soils, but its performance in persistently wet grassland systems remains uncertain. This is particularly relevant in Irish grasslands, where soils often remain close to saturation for extended periods and seasonal waterlogging is common. Here, we evaluate the RE against three soil moisture datasets from County Wexford, Ireland, spanning different locations, soil types, and observation periods. We show that the standard RE formulation systematically over-predicts soil moisture under prolonged near-saturated conditions. We find that this arises from the commonly used Feddes plant water uptake function, which suppresses water losses under anaerobic conditions, despite continued evaporation from near-saturated soils. To address this limitation, we introduce a simple modification that retains a small non-zero water loss rate in the anaerobic regime. The modified model produces substantially improved agreement with observations across all three datasets. These results provide a systematic evaluation of RE-based soil moisture modelling in Irish grasslands. More broadly, they identify an important limitation of co
Here we report null results in the search for radio emission below $200$~MHz from six known fast radio burst sources. The observations reported here were taken using the Irish LOFAR station's high-band antennas over the course of 2020, 2021 and 2022; the cumulative observing time was $218$~h.
Electoral redistricting in Ireland's Proportional Representation Single Transferable Vote (PR-STV) system faces the challenge of selecting an optimally representative set of electoral boundaries from an enormous set of possible configurations, and where ``representative'' is a delicate balance of constitutional objectives that are often in tension with one another. We present the first computational framework for Irish electoral redistricting that systematically optimises across multiple constitutional requirements while making trade-offs explicit and quantifiable. The electoral redistricting problem is parsed using statistical physics, where constitutional objectives are considered as terms in a Potts Hamiltonian. Markov Chain Monte Carlo (MCMC) methods and simulated annealing are employed to minimise this objective function, systematically exploring this configuration space, with coupling constants as proxies for objective weightings. Multi Criterion Decision Analysis (MCDA) and Pareto Optimality is then utilised to remedy the ambiguity in choosing a certain objective weighting combination over others. With respect to proportional representation and compactness objectives evaluat
Pulsar timing is a foundational part of pulsar research to triage the most interesting systems and to characterise properties (rotational or otherwise) of the population of these extreme objects. Due to the efficiency of a number of sensitive and/or wide-field surveys in recent years, the number of new pulsars discoveries is growing year-on-year, and most of these lack even basic timing parameter measurements. This work aims to demonstrate the capabilities of international Low Frequency Array (LOFAR) stations operating as single telescopes to follow-up, time and characterise these sources, offering new insight into the emission properties of these neutron stars, and support efforts to build timing models for these sources. Between 2020 and 2023 we used the local-mode allocation of the Irish LOFAR station to follow-up 33 pulsar candidates announced from various surveys at different observing frequencies to determine if an international LOFAR station has sufficient sensitivity to detect and time these sources. From the 33 pulsars selected, 22 pulsars were detected and 17 were selected for long-term monitoring across 590 hours of observing time. This has resulted in coherent timing so
This work presents a wavelet-based approach to time-frequency fingerprinting for time series feature extraction, with a focus on audio identification from live recordings of traditional Irish tunes. The challenges of identifying features in time-series data are addressed by employing a continuous wavelet transform to extract spectral features and wavelet coherence analysis is used to compare recorded audio spectrograms to synthetically generated tunes. The synthetic tunes are derived from ABC notation, which is a common symbolic representation for Irish music. Experimental results demonstrate that the wavelet-based method can accurately and efficiently identify recorded tunes. This research study also details the performance of the wavelet coherence model, highlighting its strengths over other methods of time-frequency decomposition. Additionally, we discuss and deploy the model on several applications beyond music, including in EEG signal analysis and financial time series forecasting.
Noun compounds constitute a challenging construction for NLP applications, given their variability in idiomaticity and interpretation. In this paper, we present an analysis of compound nouns identified in Irish text of varied domains by expert annotators, focusing on compositionality as a key feature, but also domain specificity, as well as familiarity and confidence of the annotator giving the ratings. Our findings and the discussion that ensued contributes towards a greater understanding of how these constructions appear in Irish language, and how they might be treated separately from English noun compounds.
Based on Irish older adult's perceptions, practices, and challenges regarding password management, the goal of this study was to compile suitable advice that can benefit this demographic. To achieve this, we first conducted semi structured interviews (n=37), we then collated advice based on best practice and what we learned from these interviews. We facilitated two independent focus groups (n=31) to evaluate and adjust this advice and tested the finalized advice through an observational study (n=15). The participants were aged between 59 and 86 and came from various counties in Ireland, both rural and urban. The findings revealed that managing multiple passwords was a significant source of frustration, leading some participants to adopt novel and informal strategies for storing them. A notable hesitation to adopt digital password managers and passphrases was also observed. Participants appreciated guidance on improving their password practices, with many affirming that securely writing down passwords was a practical strategy. Irish older adults demonstrated strong intuition regarding cybersecurity, notably expressing concerns over knowledge-based security checks used by banks and g
Fine-tuning is widely used to tailor large language models for specific tasks such as neural machine translation (NMT). However, leveraging transfer learning is computationally expensive when fine-tuning large multilingual models with billions of parameters, thus creating a barrier to entry for researchers working on low-resource domains such as Irish translation. Parameter-efficient fine-tuning (PEFT) bridges this gap by training on a fraction of the original model parameters, with the Low-Rank Adaptation (LoRA) approach introducing small, trainable adapter layers. We introduce SemiAdapt and SemiLoRA as semi-supervised inference-efficient approaches that strengthen domain adaptation and lead to improved overall performance in NMT. We demonstrate that SemiAdapt can outperform full-domain fine-tuning, while most notably, SemiLoRA can propel PEFT methods to match or even outperform full-model fine-tuning. We further evaluate domain-by-dataset fine-tuning and demonstrate that our embedding-based inference methods perform especially well on larger and noisier corpora. All Irish translation models developed in this work are released as open resources. These methods aim to make high-qual
This paper sets out the first web-based transcription system for the Irish language - Fotheidil, a system that utilises speech-related AI technologies as part of the ABAIR initiative. The system includes both off-the-shelf pre-trained voice activity detection and speaker diarisation models and models trained specifically for Irish automatic speech recognition and capitalisation and punctuation restoration. Semi-supervised learning is explored to improve the acoustic model of a modular TDNN-HMM ASR system, yielding substantial improvements for out-of-domain test sets and dialects that are underrepresented in the supervised training set. A novel approach to capitalisation and punctuation restoration involving sequence-to-sequence models is compared with the conventional approach using a classification model. Experimental results show here also substantial improvements in performance. The system will be made freely available for public use, and represents an important resource to researchers and others who transcribe Irish language materials. Human-corrected transcriptions will be collected and included in the training dataset as the system is used, which should lead to incremental im
Carbapenemase-Producing Enterobacteriace poses a critical concern for infection prevention and control in hospitals. However, predictive modeling of previously highlighted CPE-associated risks such as readmission, mortality, and extended length of stay (LOS) remains underexplored, particularly with modern deep learning approaches. This study introduces an eXplainable AI modeling framework to investigate CPE impact on patient outcomes from Electronic Medical Records data of an Irish hospital. We analyzed an inpatient dataset from an Irish acute hospital, incorporating diagnostic codes, ward transitions, patient demographics, infection-related variables and contact network features. Several Transformer-based architectures were benchmarked alongside traditional machine learning models. Clinical outcomes were predicted, and XAI techniques were applied to interpret model decisions. Our framework successfully demonstrated the utility of Transformer-based models, with TabTransformer consistently outperforming baselines across multiple clinical prediction tasks, especially for CPE acquisition (AUROC and sensitivity). We found infection-related features, including historical hospital exposu
Mycotoxin contamination poses a significant risk to cereal crop quality, food safety, and agricultural productivity. Accurate prediction of mycotoxin levels can support early intervention strategies and reduce economic losses. This study investigates the use of neural networks and transfer learning models to predict mycotoxin contamination in Irish oat crops as a multi-response prediction task. Our dataset comprises oat samples collected in Ireland, containing a mix of environmental, agronomic, and geographical predictors. Five modelling approaches were evaluated: a baseline multilayer perceptron (MLP), an MLP with pre-training, and three transfer learning models; TabPFN, TabNet, and FT-Transformer. Model performance was evaluated using regression (RMSE, $R^2$) and classification (AUC, F1) metrics, with results reported per toxin and on average. Additionally, permutation-based variable importance analysis was conducted to identify the most influential predictors across both prediction tasks. The transfer learning approach TabPFN provided the overall best performance, followed by the baseline MLP. Our variable importance analysis revealed that weather history patterns in the 90-day
Ireland's coastline, a critical and dynamic resource, is facing challenges such as erosion, sedimentation, and human activities. Monitoring these changes is a complex task we approach using a combination of satellite imagery and deep learning methods. However, limited research exists in this area, particularly for Ireland. This paper presents the Landsat Irish Coastal Segmentation (LICS) dataset, which aims to facilitate the development of deep learning methods for coastal water body segmentation while addressing modelling challenges specific to Irish meteorology and coastal types. The dataset is used to evaluate various automated approaches for segmentation, with U-NET achieving the highest accuracy of 95.0% among deep learning methods. Nevertheless, the Normalised Difference Water Index (NDWI) benchmark outperformed U-NET with an average accuracy of 97.2%. The study suggests that deep learning approaches can be further improved with more accurate training data and by considering alternative measurements of erosion. The LICS dataset and code are freely available to support reproducible research and further advancements in coastal monitoring efforts.
Translation models for the specific domain of translating Covid data from English to Irish were developed for the LoResMT 2021 shared task. Domain adaptation techniques, using a Covid-adapted generic 55k corpus from the Directorate General of Translation, were applied. Fine-tuning, mixed fine-tuning and combined dataset approaches were compared with models trained on an extended in-domain dataset. As part of this study, an English-Irish dataset of Covid related data, from the Health and Education domains, was developed. The highest-performing model used a Transformer architecture trained with an extended in-domain Covid dataset. In the context of this study, we have demonstrated that extending an 8k in-domain baseline dataset by just 5k lines improved the BLEU score by 27 points.
For over a decade, complex networks have been applied to mythological texts in order to quantitatively compare them. This has allowed us to identify similarities between texts in different cultures, as well as to quantify the significance of some heroic characters. Analysing a full mythology of a culture requires gathering data from many individual myths which is time consuming and often impractical. In this work, we attempt to bypass this by analysing the network of characters in a dictionary of mythological characters. We show that the top characters identified by different centrality measures are consistent with central figures in the Irish sagas. Although much of Irish mythology has been lost, we demonstrate that these most central characters are highly robust to a large random removal of edges.