AIarXiv
Ranked by formulaVerdict: NotableParameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir Language
Bashkir is a low-resource agglutinative language written in Cyrillic and remains poorly represented in modern LLMs.
Caveats
- Preprint; not yet peer reviewed.
VerdictWorth a reader's time today.
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), 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 =0.084). (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.
The editor's rubric
- Leverage4 / 5
- A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).
- Magnitude4 / 5
- A qualitative jump: a capability or regime that did not exist before.
- Evidence4 / 5
- Strong: large scale, preregistered, independently replicated, or a well-powered randomized trial.
- Novelty2 / 5
- A new combination of known ideas.
- Trajectory3 / 5
- A clear path to scale.
- Stakes2 / 5
- Benefits a professional community (practitioners, clinicians, engineers).
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); breadth (many tasks, zero/few-shot); gains (x-fold, versus baseline, outperforms); verification (p-value, error bars, multiple benchmarks); scale (efficient); stakes (general AI). Red flags: derivative (comparative study).
How the score was computed
Desks place stronger verdicts first, then use this score to order work within the same verdict.
- Merit
- 6.6 / 10
- Adjusted merit
- 5.3 / 10
- Attention
- 0%
- Freshness
- 87%