GaelEval: Benchmarking LLM Performance for Scottish Gaelic
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914440264286208 |
|---|---|
| author | Devine, Peter Lamb, William Alex, Beatrice Ezeani, Ignatius Knight, Dawn Meachair, Mícheál J. Ó Rayson, Paul Wynne, Martin |
| author_facet | Devine, Peter Lamb, William Alex, Beatrice Ezeani, Ignatius Knight, Dawn Meachair, Mícheál J. Ó Rayson, Paul Wynne, Martin |
| contents | Multilingual large language models (LLMs) often exhibit emergent 'shadow' capabilities in languages without official support, yet their performance on these languages remains uneven and under-measured. This is particularly acute for morphosyntactically rich minority languages such as Scottish Gaelic, where translation benchmarks fail to capture structural competence. We introduce GaelEval, the first multi-dimensional benchmark for Gaelic, comprising: (i) an expert-authored morphosyntactic MCQA task; (ii) a culturally grounded translation benchmark and (iii) a large-scale cultural knowledge Q&A task. Evaluating 19 LLMs against a fluent-speaker human baseline ($n=30$), we find that Gemini 3 Pro Preview achieves $83.3\%$ accuracy on the linguistic task, surpassing the human baseline ($78.1\%$). Proprietary models consistently outperform open-weight systems, and in-language (Gaelic) prompting yields a small but stable advantage (+$2.4\%$). On the cultural task, leading models exceed $90\%$ accuracy, though most systems perform worse under Gaelic prompting and absolute scores are inflated relative to the manual benchmark. Overall, GaelEval reveals that frontier models achieve above-human performance on several dimensions of Gaelic grammar, demonstrates the effect of Gaelic prompting and shows a consistent performance gap favouring proprietary over open-weight models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02135 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GaelEval: Benchmarking LLM Performance for Scottish Gaelic Devine, Peter Lamb, William Alex, Beatrice Ezeani, Ignatius Knight, Dawn Meachair, Mícheál J. Ó Rayson, Paul Wynne, Martin Computation and Language Multilingual large language models (LLMs) often exhibit emergent 'shadow' capabilities in languages without official support, yet their performance on these languages remains uneven and under-measured. This is particularly acute for morphosyntactically rich minority languages such as Scottish Gaelic, where translation benchmarks fail to capture structural competence. We introduce GaelEval, the first multi-dimensional benchmark for Gaelic, comprising: (i) an expert-authored morphosyntactic MCQA task; (ii) a culturally grounded translation benchmark and (iii) a large-scale cultural knowledge Q&A task. Evaluating 19 LLMs against a fluent-speaker human baseline ($n=30$), we find that Gemini 3 Pro Preview achieves $83.3\%$ accuracy on the linguistic task, surpassing the human baseline ($78.1\%$). Proprietary models consistently outperform open-weight systems, and in-language (Gaelic) prompting yields a small but stable advantage (+$2.4\%$). On the cultural task, leading models exceed $90\%$ accuracy, though most systems perform worse under Gaelic prompting and absolute scores are inflated relative to the manual benchmark. Overall, GaelEval reveals that frontier models achieve above-human performance on several dimensions of Gaelic grammar, demonstrates the effect of Gaelic prompting and shows a consistent performance gap favouring proprietary over open-weight models. |
| title | GaelEval: Benchmarking LLM Performance for Scottish Gaelic |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.02135 |