Newest papers

Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir Language

Mullosharaf K. Arabov, Svetlana S. Khaybullina · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31397 · open-access PDF

French

Bashkir est un langage agglutinatif à faible ressource écrit en cyrillique et reste mal représenté dans les LLM modernes. Nous présentons une suite de ressources ouvertes et un benchmark systématique des méthodes d'adaptation: le Bashkir Web Corpus (71,567 documents, 46,9M jetons, 16 sources) et trois ensembles de données étiquetés pour la classification du texte binaire, multiclass et multilabel; le benchmark couvre les deux premiers.

Machine translation (Meta M2M100); the English original follows.

Abstract

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)

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31397, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange