Qwen2 technical report

A Yang, B Yang, B Hui, B Zheng, B Yu, C Zhou… - arXiv preprint arXiv …, 2024 - arxiv.org
This report introduces the Qwen2 series, the latest addition to our large language models
and large multimodal models. We release a comprehensive suite of foundational and …

Vikhr: Constructing a State-of-the-art Bilingual Open-Source Instruction-Following Large Language Model for Russian

A Nikolich, K Korolev, S Bratchikov… - Proceedings of the …, 2024 - aclanthology.org
There has been a surge in the development of various Large Language Models (LLMs).
However, text generation for languages other than English often faces significant …

Key Algorithms for Keyphrase Generation: Instruction-Based LLMs for Russian Scientific Keyphrases

A Glazkova, D Morozov, T Garipov - arXiv preprint arXiv:2410.18040, 2024 - arxiv.org
Keyphrase selection is a challenging task in natural language processing that has a wide
range of applications. Adapting existing supervised and unsupervised solutions for the …

RuBia: A Russian Language Bias Detection Dataset

V Grigoreva, A Ivanova, I Alimova… - arXiv preprint arXiv …, 2024 - arxiv.org
Warning: this work contains upsetting or disturbing content. Large language models (LLMs)
tend to learn the social and cultural biases present in the raw pre-training data. To test if an …

Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian

A Nikolich, K Korolev, A Shelmanov - arXiv preprint arXiv:2405.13929, 2024 - arxiv.org
There has been a surge in the development of various Large Language Models (LLMs).
However, text generation for languages other than English often faces significant …

Long Input Benchmark for Russian Analysis

I Churin, M Apishev, M Tikhonova, D Shevelev… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advancements in Natural Language Processing (NLP) have fostered the
development of Large Language Models (LLMs) that can solve an immense variety of tasks …

Improving Large Language Model Russian Adaptation with Preliminary Vocabulary Optimization

MM Tikhomirov, DI Chernyshev - Lobachevskii Journal of Mathematics, 2024 - Springer
Abstract Most of Large Language Model (LLM) text comprehension capabilities come from
generative pre-training on large corpora which includes texts of different domains …