<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">humanitieslaw</journal-id><journal-title-group><journal-title xml:lang="ru">Гуманитарные и юридические исследования</journal-title><trans-title-group xml:lang="en"><trans-title>Humanities and law research</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2409-1030</issn><publisher><publisher-name>North-Caucasus Federal University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.37493/2409-1030.2025.3.20</article-id><article-id custom-type="elpub" pub-id-type="custom">humanitieslaw-1615</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ФИЛОЛОГИЧЕСКИЕ НАУКИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>PHILOLOGICAL SCIENCES</subject></subj-group></article-categories><title-group><article-title>Интерпретация художественного приёма в тексте лингвистическими нейросетями Алиса YandexGPT 5 Pro, GPT-4o DUM-E, DeepSeek Рико и GigaChat</article-title><trans-title-group xml:lang="en"><trans-title>Interpretation of figurative language in text by linguistic neural networks Alice YandexGPT 5 Pro, GPT-4o DUM-E, DeepSeek Rico and GigaChat</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-9245-2255</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гусаренко</surname><given-names>С. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Gusarenko</surname><given-names>S. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сергей Викторович Гусаренко - Доктор филологических наук, профессор</p><p>д.1, ул. Пушкина, Ставрополь, 355017</p></bio><bio xml:lang="en"><p>Sergey V. Gusarenko - Dr. Sc. (Philology), Professor</p><p>1, Pushkina St., Stavropol, 355017</p></bio><email xlink:type="simple">gusarenko@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-9312-8621</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гусаренко</surname><given-names>М. К.</given-names></name><name name-style="western" xml:lang="en"><surname>Gusarenko</surname><given-names>M. K.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Марина Константиновна Гусаренко - Кандидат филологических наук, доцент</p><p>д.1, ул. Пушкина, Ставрополь, 355017</p></bio><bio xml:lang="en"><p>Marina K. Gusarenko - Cand. Sc. (Philology), Associate Professor</p><p>1, Pushkina St., Stavropol, 355017</p></bio><email xlink:type="simple">mkgusarenko@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Северо-Кавказский федеральный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>North-Caucasus Federal University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>10</day><month>11</month><year>2025</year></pub-date><volume>12</volume><issue>3</issue><fpage>513</fpage><lpage>523</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Гусаренко С.В., Гусаренко М.К., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Гусаренко С.В., Гусаренко М.К.</copyright-holder><copyright-holder xml:lang="en">Gusarenko S.V., Gusarenko M.K.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://humanitieslaw.ncfu.ru/jour/article/view/1615">https://humanitieslaw.ncfu.ru/jour/article/view/1615</self-uri><abstract><sec><title>Введение</title><p>Введение. Цель исследования состояла в изучении способностей нейросетей Алиса YandexGPT 5 Pro, GPT-4o DUM-E, DeepSeek Рико, GigaChat к адекватной интерпретации художественных текстов. Было проведено изучение следующих возможностей этих языковых нейросетей: идентификация в тексте художественного приёма; применение языка метаописания; распознавание и характеристика прецедентных феноменов – исторических персонажей, событий, явлений; распознавание и интерпретация метафоры и гиперболы; интерпретация семантически сложного выражения в контексте.</p></sec><sec><title>Материалы и методы</title><p>Материалы и методы. В качестве материала исследования избран фрагмент первой главы романа И. Ильфа и Е. Петрова «Золотой телёнок». В качестве основных использовались метод макроструктурного анализа, метод интерпретационного анализа, процедурно-семантического анализа.</p></sec><sec><title>Анализ</title><p>Анализ. В ходе исследования в ответах – интерпретациях нейросетей выделялись рематические элементы, сводились в единую таблицу и подвергались семантическому и сопоставительному анализу, в ходе которого выявлялись как успешные интерпретации, так и отрицательные результаты.</p></sec><sec><title>Результаты</title><p>Результаты. Установлено, что изучаемые языковые нейросети способны успешно идентифицировать художественный приём в анализируемом тексте. Так, названные нейросети адекватно интерпретировали обращение авторов к прецедентным именам, при этом они также адекватно определили цели этого обращения: создание контраста, расширение временных рамок повествования. При единообразной идентификации приёма – создание контраста – четыре разные нейросети также единообразно определили противопоставляемые семантические объекты в глубинной семантике текста, при этом по-разному определили репрезентацию этих объектов в поверхностных структурах. Нейросети Алиса YandexGPT 5 Pro и GPT DUM-E идентифицировали гиперболу как художественный приём, причём Алиса только констатировала художественный приём, между тем как нейросеть DUM-E определила его содержание. Также был выявлен ряд дефектов в интерпретации текста нейросетями.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>Introduction</title><p>Introduction. The purpose of the research was to study the abilities of the neural networks Alice YandexGPT 5 Pro, GPT-4o DUM-E, DeepSeek Rico, GigaChat to adequately interpret literary texts. The following possibilities of these linguistic neural networks were studied: identification of a stylistic device in the text; application of the language of meta-description; recognition and characterization of precedent phenomena – historical characters, events, phenomena; recognition and interpretation of metaphor and hyperbole; interpretation of semantically complex expressions in context.</p></sec><sec><title>Materials and methods</title><p>Materials and methods. A fragment of the first chapter of the novel The Golden Calf by I. Ilf and E. Petrov was chosen as the research material. The method of macrostructural analysis, the method of interpretative analysis, and procedural-semantic analysis were used as the main ones.</p></sec><sec><title>Analysis</title><p>Analysis. In the course of the study, rhematic elements were identified in the responses-interpretations of neural networks, summarized in a single table and subjected to semantic and comparative analysis, which revealed both successful interpretations and negative results.</p></sec><sec><title>Results</title><p>Results. It is shown that the studied language neural networks als and methods. A fragment of the first chapter of the novel The Golden Calf by I. Ilf and E. Petrov was chosen as the research material. The method of macrostructural analysis, the method of interpretative analysis, and procedural-semantic analysis were used as the main ones. Analysis. In the course of the study, rhematic elements were identified in the responses-interpretations of neural networks, summarized in a single table and subjected to semantic and comparative analysis, which revealed both successful interpretations and negative results. Results. It is shown that the studied language neural networks.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>текст</kwd><kwd>интерпретация</kwd><kwd>языковая нейросеть</kwd><kwd>художественный приём</kwd><kwd>прецедентный феномен</kwd><kwd>гипербола</kwd></kwd-group><kwd-group xml:lang="en"><kwd>text</kwd><kwd>interpretation</kwd><kwd>linguistic neural network</kwd><kwd>stylistic device</kwd><kwd>precedent phenomenon</kwd><kwd>hyperbole</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Алиса YandexGPT 5 Pro. URL: https://alice.yandex.ru/ (дата обращения: 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">Alice YandexGPT 5 Pro. Available from: https://alice.yandex.ru/ [Accessed 25 June 2025]. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Арутюнова Н. Д. Предложение и его смысл: логико-семантические проблемы: монография. М.: Наука, 1976. 383 с.</mixed-citation><mixed-citation xml:lang="en">Arutyunova ND. The sentence and its meaning: logical-semantic problems. Moskow: Nauka; 1976. 383 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Грайс Г. П. Логика и речевое общение // Новое в зарубежной лингвистике: Лингвистическая прагматика. 1985. Вып. XVI. С. 217–237.</mixed-citation><mixed-citation xml:lang="en">Grice GP. Logics and conversation. New in foreign linguistics: Linguistic pragmatics. Moscow: Progress; 1985;(XVI):217-237. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Гальперин И. Р. Текст как объект лингвистического исследования. М.: Едиториал УРСС, 2004. 144 с.</mixed-citation><mixed-citation xml:lang="en">Galperin IR. Text as an object of linguistic research. Moscow: Editorial URSS; 2004. 144 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Дейк Т. А. ван Кинч В. Стратегии понимания связного текста // Новое в зарубежной лингвистике: Когнитивные аспекты языка. 1988. Вып. XXIII. С. 153–211.</mixed-citation><mixed-citation xml:lang="en">Deik TA. van, Kinch V. Strategies for understanding a coherent text. New in foreign linguistics: Cognitive aspects of language. 1988;(XXIII):153-211. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Падучева Е. В. Высказывание и его соотнесенность с действительностью (референциальные аспекты семантики местоимений). 4-е изд. М.: Едиториал, 2004. 288 с.</mixed-citation><mixed-citation xml:lang="en">Paducheva EV. Utterance and its correlation with reality (referential aspects of the semantics of pronouns). 4th ed. Moscow: Editorial; 2004. 288 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Bazin H. Are Large Language Models capable of Gricean conversational implicatures? URL: https://sopha2025.sciencesconf.org/browse/author?authorid=1323099 (дата обращения: 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">Bazin H. Are Large Language Models capable of Gricean conversational implicatures? Available from: https://sopha2025.sciencesconf.org/browse/author?authorid=1323099 [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">DeepSeek Рико. URL: https://web.telegram.org/a/#6433748390 (дата обращения: 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">DeepSeek Rico. Available from: https://web.telegram.org/a/#6433748390 [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Emmy L., Chenxuan C., Kenneth Zh, Graham N. Testing the Ability of Language Models to Interpret Figurative Language. URL: https://arxiv.org/pdf/2204.12632v1 (дата обращения: 07.07.2025).</mixed-citation><mixed-citation xml:lang="en">Testing the Ability of Language Models to Interpret Figurative Language / L. Emmy, C. Chenxuan, Zh. Kenneth, N. Graham. Available from: https://arxiv.org/pdf/2204.12632v1 [Accessed 25 July 2025].</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">GigaChat. URL: https://web.telegram.org/a/#6218783903 (дата обращения: 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">GigaChat. Available from: https://web.telegram.org/a/#6218783903 [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">GPT-4o DUM-E. URL: https://web.telegram.org/a/#6010034370 (дата обращения: 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">GPT-4o DUM-E. Available from: https://web.telegram.org/a/#6010034370 [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Cultural Evaluation of LLMs in Russian: Catchphrases and Cultural Types / E. Gromenko, D. Kalacheva, K. Klokova, M. Krongauz, O. Moroz, V. Shulginov, T. Yudina. URL: https://dialogue-conf.org/wp-content/uploads/2025/06/GromenkoEetal.029.pdf (дата обращения 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">Gromenko E., Kalacheva D., Klokova K., Krongauz M., Moroz O., Shulginov V., Yudina T. Cultural Evaluation of LLMs in Russian: Catchphrases and Cultural Types. Available from: https://dialogue-conf.org/wp-content/uploads/2025/06/GromenkoEetal.029.pdf [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE / Y. Gu, Y. Fu, V. Pyatkin, I. Magnusson, B. D. Mishra, P. Clark. URL: https://arxiv.org/pdf/2210.16407 (дата обращения 07.07.2025).</mixed-citation><mixed-citation xml:lang="en">Gu Y., Fu Y., Pyatkin V., Magnusson I., Mishra B.D., Clark P. Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE. URL: https://arxiv.org/pdf/2210.16407 [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">The development of a natural language reasoning system for a companion robot / A. A. Kotov, A. A. Filatov, Z. A. Nosovets, N. A. Arinkin. URL: https://dialogue-conf.org/wp-content/uploads/2025/06/KotovAAetal.077.pdf (дата обращения 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">Kotov A.A., Filatov A.A., Nosovets Z.A., Arinkin N.A. The development of a natural language reasoning system for a companion robot. URL: https://dialogue-conf.org/wp-content/uploads/2025/06/KotovAAetal.077.pdf [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Evaluating the Pragmatic Competence of Large Language Models in Detecting Mitigated and Unmitigated Types of Disagreement / V. Shulginov, H. B. Şimşek, S. Kudriashov, S. A. Shevela, R. Randavtsova. URL: https://dialogue-conf.org/wpcontent/uploads/2025/06/ShulginovVetal.037.pdf (дата обращения 25.06.2025).</mixed-citation><mixed-citation xml:lang="en">Shulginov V., Şimşek H.B., Kudriashov S., Shevela S.A., Randavtsova R. Evaluating the Pragmatic Competence of Large Language Models in Detecting Mitigated and Unmitigated Types of Disagreement. Available from: https://dialogueconf.org/wp-content/uploads/2025/06/ShulginovVetal.037.pdf [Accessed 25 June 2025].</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
