Journal archive

Abstract: This article examines lexical means of argumentation in Eugene Vodolazkin’s novel Laurus using different methods of working with large language models (LLMs). The object of the study comprises lexico-discursive units that perform an argumentative function in specific speech situations and participate in the justification of evaluation, action, or moral-religious idea, in the marking of the source and degree of reliability of knowledge, and in the interpretation of events. The aim of the study is to identify and describe the lexico-discursive units with an argumentative function on the basis of four fragments of the novel representing different speech situations. The methodology combines functional-semantic, discourse, and contextual analysis with preliminary LLM-assisted text processing and subsequent manual linguistic verification according to the following criteria: the unit’s inclusion in the corpus in question, quotation accuracy, and its syntactic role and argumentative function. The study is qualitative and fragment-based in nature and does not purport to provide a statistical description of the novel as a whole. The findings are therefore limited by the composition of the corpus, the wording of the instruction used, and the conditions of the preliminary LLM-assisted analysis. The study singles out three functional groups: argumentative markers proper, epistemic-modal and rhetorical-pragmatic constructions, and contextually argumentative lexical units. It is shown that, in the analyzed fragments, the justification of evaluation and moral-religious positions, as well as the marking of the source and degree of reliability of knowledge, is realized not only through explicit causal, consequential, and inferential markers, but also through lexical units the argumentative function of which emerges in a particular context. The theoretical significance of the study lies in distinguishing between direct and context-dependent realizations of the argumentative function of linguistic units in literary texts and in refining the criteria for their functional classification in specific speech situations. The practical significance of the findings is associated with their potential application to linguistic analysis of literary discourse, the development of LLM-assisted procedures of annotating textual material, and the development of university courses in text linguistics, discourse analysis, and digital humanities. It has been found that, within the given corpus and under a unified instruction, the three LLM interfaces used in the study exhibited different types of limitations: crossing the boundaries of the corpus, a predominant orientation toward explicit markers, and the overinclusive classification of thematic or emotionally evaluative units as argumentative.

About the author(s) :

Irina I. Mitrofanova

RUDN University (Moscow, Russian Federation)

ORCID ID: https://orcid.org/0000-0003-0532-8841

Ping Gong

RUDN University (Moscow, Russian Federation)

ORCID ID: https://orcid.org/0009-0009-6062-5575

Publication Timeline:

Date of receipt: 21.06.2026; date of publication: 31.10.2026

References:

Akazawa, M., Gius, E. (2025). Literaturwissenschaftlich Arbeiten mit großen Sprachmodellen? Zeitschrift fur Literaturwissenschaft und Linguistik, 55(2), 449–474. DOI: 10.1007/s41244-025-00383-4. EDN PMAXLO.

Alekseev, A. P. (2013). Teoriya argumentatsii v epokhu manipulyatsiy = Argumentation theory in the age of manipulation. Bulletin of Moscow University. Series 7: Philosophy, 5, 67–77. EDN REVUWP.

Amanғazyқyzy, M., Gylya, A., Siryachenko, V. V. (2024). Tsifrovoe literaturovedenie: obzor praktik i perspektivy v kazakhstanskom literaturovedenii = Digital literary studies: A review of practices and prospects in Kazakhstani literary studies. Bulletin of Shokan Ualikhanov Kokshetau University Philological Series, 4, 300–314. DOI: 10.59102/kufil/2024/iss4pp300-314. EDN CSEPGT.

Bender, E. M., Gebru, T., McMillan-Major, A., Shmitchell, S. (2021). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–623. New York: ACM. DOI: 10.1145/3442188.3445922.

Chang, Y., Wang, X., Wang, J. et al. (2024). A Survey on Evaluation of Large Language Models. ACM Transactions on Intelligent Systems and Technology, 15(3). Article 39, 1–45. DOI: 10.1145/3641289.

Devlin, J., Chang, M.-W., Lee, K., Toutanova, K. (2019). BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (volume 1 (Long and Short Papers)), 4171–4186. Minneapolis: Association for Computational Linguistics. DOI: 10.18653/v1/N19-1423.

Gavrishina, I. N. (2018). Lingvisticheski orientirovannye kontseptsii argumentatsii = Linguistically oriented concepts of argumentation. Philological Sciences. Issues of Theory and Practice, 12-1(90), 99–104. DOI: 10.30853/filnauki.2018-12-1.21. EDN VMVBQR.

Grigorieva, V. S. (2022). Kognitivnyy rakurs argumentatsii = Cognitive perspective of argumentation. Cherepovets State University Bulletin, 6(111), 140–150. DOI: 10.23859/1994-0637-2022-6-111-11. EDN JSVUVS.

Habernal, I., Gurevych, I. (2017). Argumentation mining in user-generated web discourse. Computational Linguistics, 43(1), 125–179. DOI: 10.1162/COLI_a_00276. EDN YYMNPV.

Hatzel, H. O., Stiemer, H., Biemann, Ch., Gius, E. (2023). Machine learning in computational literary studies. IT. Information Technology, 65(4-5), 200–217. DOI: 10.1515/itit-2023-0041. EDN EHPHHF.

Ioanesyan, E. R. (2020). Implitsitnaya otsenka i argumentatsiya = Implicit evaluation and argumentation. Scientific Dialogue, 1, 62–77. DOI: 10.24224/2227-1295-2020-1-62-77. EDN ATOYFX.

Kodotsigova, O. (2026). Khudozhestvennoe vremya v drevnerusskoy agiografii i romane Evgeniya Vodolazkina Lavr = Artistic time in Old Russian hagiography and in Evgeny Vodolazkin’s novel Laurus. Slovo, 15(1/2025), 45–57. DOI: 10.62229/slv15/3. EDN VTUSOC.

Kuzina, E. B. (2019). Argumentatsiya v dokazatel′stve = Argumentation in proof. Values and Meanings, 6(64), 131–143. DOI: 10.24411/2071-6427-2019-10102. EDN APNXCE.

Lawrence, J., Reed, C. (2019). Argument mining: A survey. Computational Linguistics, 45(4), 765–818. DOI: 10.1162/COLIa00364. EDN UCODMA.

Lippi, M., Torroni, P. (2016). Argumentation Mining: State of the Art and Emerging Trends. ACM Transactions on Internet Technology, 16(2). Article 10, 1–25. DOI: 10.1145/2850417.

Shurinova, N. S. (2016). «Mertvyy yazyk» kak sredstvo voskresheniya sub′′ektivnosti «drugogo» v romane E. G. Vodolazkina «Lavr» = “Dead language” as a means of resurrecting the subjectivity of the “Other” in E. G. Vodolazkin’s novel “Laurus”. The New Past, 4, 99–110. DOI: 10.18522/2500-3224-2016-4-99-110. EDN XISDDJ.

Stab, C., Gurevych, I. (2017). Parsing Argumentation Structures in Persuasive Essays. Computational Linguistics, 43(3), 619–659. DOI: 10.1162/COLI_a_00295.

Zhao, W. X., Zhou, K., Li, Ju. et al. (2026). A Survey of Large Language Models. Frontiers of Computer Science, 20(12), 2012627. DOI: 10.1007/s11704-026-60308-3. EDN PQJLPV.