Metraipolis › archive › dc_7f69a6b70692
Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir… — arXiv:2610.31397
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31397
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-23T15:20:40.354Z
- SHA-256 of the archived text
388e3edff61da3616e1b9ad4fa899c43d9a1b46e10bfe43299aaf08e7525dd3d- Stable URL of this page
https://metraipolis.com/documento/dc_7f69a6b70692
How to cite
Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir… — arXiv:2610.31397 — arXiv (en), https://arxiv.org/abs/2610.31397 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f69a6b70692 (Metraipolis archive dc_7f69a6b70692, sha256 388e3edff61da3616e1b9ad4fa899c43d9a1b46e10bfe43299aaf08e7525dd3d)
BibTeX
@misc{dc7f69a6b70692,
title = {Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir… — arXiv:2610.31397},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31397},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f69a6b70692; sha256 388e3edff61da3616e1b9ad4fa899c43d9a1b46e10bfe43299aaf08e7525dd3d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31397. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Bashkir is a low-resource agglutinative language written in Cyrillic and remains poorly represented in modern LLMs. We present an open resource suite and a systematic benchmark of adaptation methods: the Bashkir Web Corpus (71,567 documents, 46.9M tokens, 16 sources) and three labelled datasets for binary, multiclass and multilabel text classification; the benchmark covers the first two. Experiments use eight architectures (82M-8B: DistilGPT2, GPT-2 base/medium, Phi-3-mini, Mistral-7B, YandexGPT-5-Lite-8B, mBERT, XLM-R) and three adaptation groups (full fine-tuning, QLoRA, in-context learning), plus continual pretraining (CPT). (1) QLoRA on 3.8-8B models outperforms encoder-only fine-tuning on binary classification: YandexGPT-5-Lite-8B with CPT reaches macro-F1 0.748 vs 0.653 (XLM-R) and 0.650 (mBERT); pairwise differences are significant after Holm correction (p<0.001). (2) YandexGPT-5-Lite-8B significantly outperforms Mistral-7B and Phi-3-mini on multiclass classification, BPB and native-speaker ratings (mean 3.28 vs 2.52 and 2.22; n=100; alpha=0.69-0.77; p<0.05); on binary classification its QLoRA advantage is not significant (p>=0.084). (3) CPT effects depend on model and task: perplexity improves for Phi-3-mini (+0.58) and YandexGPT-5-Lite-8B (+0.33) but worsens for Mistral-7B (-1.15, p<0.001); on binary classification CPT helps Mistral-7B most (+4.0 macro-F1). (4) Tokeniser fertility on Bashkir varies 2.67x (2.92-7.80) and tracks adaptation quality, while perplexity across tokenisers is not comparable. Cyrillic tokenisers with Russian pretraining are preferable; LLM judges reproduce native ratings for grammar and coherence (rho=0.33-0.46) but not language correctness (rho=0.16, p=0.11); native evaluation remains necessary. All artefacts are open-licensed. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.31397 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-23T15:09:38.360Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).