Generating coherent, semantically accurate text from large structured inputs remains a persistent challenge in data-to-text generation, as single-step LLM mappings from data-to-text limit control over discourse structuring and amplify hallucinations and omissions as input size grows. We introduce a new dataset of extended DBpedia triple sets (up to 199 triples per input), and a modular multi-agent framework: specialised LLM agents handle content ordering, text structuring, and surface realisation under the supervision of an orchestrator and guardrail control loop. The system generates multi-paragraph outputs in English and Irish (low-resource). We compare a three-worker multi-agent configuration against a single-worker multi-task variant and a strong end-to-end baseline. Quality is assessed via human evaluation and LLM-as-a-judge (with truncation-based sanity checks). Results show slightly superior coherence for the multi-agent approach in both languages, with statistically significant inter-rater correlation over all criteria for English and no statistically significant correlation for Irish. Human-LLM alignment is very weak overall, thus exposing key limits in scalable NLG evaluation.

Minority languages such as Irish are massively under-resourced, particularly in terms of high-quality domain-relevant data, limiting the capabilities of machine translation (MT) engines, even those integrating large language models (LLMs). The eSTÓR project, described in this paper, focuses on the collection and curation of high-quality Irish text data for diverse domains.

The Irish language has been deemed ‘definitely endangered’ (Moseley, 2012) and has been clas- sified as having ‘weak or no support’ (Lynn, 2023) regarding digital resources in spite of its status as the first official and national language of the Republic of Ireland. This research de- velops the first named entity recognition (NER) tool for the Irish language, one of the essen- tial tasks identified by the Digital Plan for Irish (Ní Chasaide et al., 2022). In this study, we produce a small gold-standard NER-annotated corpus and compare both monolingual and mul- tilingual BERT models fine-tuned on this task. We experiment with different model architec- tures and low-resource language approaches to enrich our dataset. We test our models on a mix of single- and multi-word named entities as well as a specific multi-word named entity test set. Our proposed gaBERT model with the implementation of random data augmentation and a conditional random fields layer demon- strates significant performance improvements over baseline models, alternative architectures, and multilingual models, achieving an F1 score of 76.52. This study contributes to advanc- ing Irish language technologies and supporting Irish language digital resources, providing a basis for Irish NER and identification of other MWE types.