LLM Applications to the task of Word Sense Disambiguation in Russian texts
Main Article Content
Abstract
This study is dedicated to experiments in Word Sense Disambiguation on Russian-language material using generative (decoder-only) models of small and medium size. While the direct application of generative models is not an optimal approach for this task, such models demonstrate potential as semantic annotators of large volumes of raw data. The automation of semantic text annotation using generative models may help overcome the bottleneck of insufficient labeled data for training encoder-based models.
Previous studies show that state-of-the-art English and multilingual models can achieve accuracy above 90% on this task, while smaller models typically reach 80%+. The present study aims to determine whether a comparable task can be successfully addressed for small- and medium-scale models adapted to Russian, that do not require substantial computational resources.
The experiments reported in this paper are conducted both in a basic setting (one/few-shot prompting) with separate tests for narrow and broad context windows of the ambiguous lexeme, as well as under several modifications, such as context enrichment with paradigmatic information (e.g., hypernyms, hyponyms, domain labels of the target word) and ensemble approaches in which one model validates and refines the predictions of another. The study is based on the Russian annotated resource RuSemCor, annotated in terms of the RuWordNet semantic net.
The experiments ultimately pursue the development of an efficient and accessible pipeline for automatic semantic annotation of Russian texts, useful both for direct application and for preparing annotated data for machinelearning tasks.
Keywords:
Article Details
References
2. Navigli R., Ponzetto S.P. BabelNet: Building a very large multilingual semantic network // Proceedings of the 48th annual meeting of the association for computational linguistics. 2010. P. 216–225.
3. Maru M. et al. SyntagNet: Challenging supervised word sense disambiguation with lexical-semantic combinations // Proc. of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019. P. 3534–3540.
4. Loukachevitch N.V., Lashevich G., Gerasimova A.A., Ivanov V.V., Dobrov B.V. Creating Russian WordNet by Conversion // Proc. of Conference on Computational Linguistics and Intellectual Technologies Dialog-2016, 2016. P. 405–415.
5. Yae J.H. et al. Leveraging large language models for word sense disambiguation // Neural Computing and Applications. 2025. Vol. 37, No. 6. P. 4093–4110. https://doi.org/10.1007/s00521-024-10747-5
6. Sumanathilaka D., Micallef N., Hough J. Glossgpt: Gpt for word sense disambiguation using few-shot chain-of-thought prompting //Procedia Computer Science. 2025. Vol. 257. P. 785–792. https://doi.org/10.1016/j.procs.2025.03.101
7. Kirillovich A. et al. RuSemCor: A Word Sense Disambiguation corpus for Russian // Proc. of the 34th ACM International Conference on Information and Knowledge Management. 2025. P. 6438–6443. https://doi.org/10.1145/3746252.3761624
8. Agirre E., Edmonds P. (Eds.). Word sense disambiguation: Algorithms and applications. Springer Science & Business Media, 2007. https://doi.org/10.1007/978-1-4020-4809-8
9. Mitrofanova O.A. et al. Avtomaticheskoe razreshenie leksiko-semanticheskoi neodnoznachnosti i vydelenie konstruktsii (na materiale Natsional'nogo korpusa russkogo yazyka) // Leksikologiya. Leksikografiya i Korpusnaya Lingvistika. 2013. P. 122–143.
10. Gusev I. Saiga_llama3_8b. Russian Llama-3-based chatbot. URL: https://huggingface.co/IlyaGusev/saiga_llama3_8b (accessed: 29.12.2025).
11. Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24. URL: https://huggingface.co/Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24 (accessed: 29.12.2025)
12. Vikhrmodels/Vistral-24B-Instruct. URL: https://huggingface.co/Vikhrmodels/Vistral-24B-Instruct (accessed:29.12.2025)
13. mistralai/Mistral-Small-24B-Instruct-2501. URL: https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501 (accessed: 29.12.2025)
14. RefalMachine/RuadaptQwen3-32B-Instruct. URL: https://huggingface.co/RefalMachine/RuadaptQwen3-32B-Instruct (accessed: 29.12.2025)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.