collaborators

12 papers

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…