12 papers
Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language
Mullosharaf K. Arabov, S. S. Pirov, B. Sultonov
This paper presents a conceptual framework for developing an electronic explanatory dictionary of the Tajik language using large language models (LLMs). The relevance of the work s…
RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation
M. K. Arabov
Multi-step symbolic reasoning is essential for robust financial analysis, yet most benchmarks neglect intermediate reasoning steps. FINCHAIN introduced verifiable Chain-of-Thought…
Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer
M. K. Arabov
Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these communities, which affects int…
Adapting Large Language Models to a Low-Resource Agglutinative Language: A Comparative Study of LoRA and QLoRA for Bashkir
Mullosharaf K. Arabov, Svetlana S. Khaybullina
This paper presents a comparative study of parameter-efficient fine-tuning (PEFT) methods, including LoRA and QLoRA, applied to the task of adapting large language models to the Ba…
TajikNLP: An Open-Source Toolkit for Comprehensive Text Processing of Tajik (Cyrillic Script)
Mullosharif K. Arabov, Karomatullo Habibullozoda, Nurali Shirinov
The Tajik language, written in Cyrillic script, remains severely under-resourced in terms of publicly available natural language processing (NLP) toolkits, hindering both linguisti…
A Systematic Benchmark of Machine Transliteration Models for the Tajik-Farsi Language Pair: A Comparative Study from Rule-Based to Transformer Architectures
Mullosharaf K. Arabov
This paper presents the first comprehensive comparative analysis of modern machine learning architectures for transliteration between Tajik (Cyrillic script) and Persian (Arabic sc…