<?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">10.37493/2409-1030.2024.4.23</article-id><article-id custom-type="elpub" pub-id-type="custom">humanitieslaw-1501</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>Функционально-семантические, макроструктурные и пресуппозиционально-прагматические параметры сгенерированных русскоязычных текстов в лингвистических нейросетях GigaChat, ChatGPT Марти и Яндекс Алиса</article-title><trans-title-group xml:lang="en"><trans-title>Functionalsemantic, macrostructural and presuppositional-pragmatic parameters of generated Russian-language texts in the linguistic neural networks GigaChat, ChatGPT Marty and Yandex Alice</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, Российская Федерация </p></bio><bio xml:lang="en"><p>Sergey V. Gusarenko -  Dr. Sc. (Philology), Professor </p><p>1, Pushkina St., 355017 Stavropol, Russian Federation </p></bio><email xlink:type="simple">sgusarenko@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, Российская Федерация </p></bio><bio xml:lang="en"><p>Marina K. Gusarenko -  Cand. Sc. (Philology), Associate Professor </p><p>1, Pushkina St., 355017 Stavropol, Russian Federation </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>2024</year></pub-date><pub-date pub-type="epub"><day>04</day><month>02</month><year>2025</year></pub-date><volume>11</volume><issue>4</issue><fpage>788</fpage><lpage>800</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/1501">https://humanitieslaw.ncfu.ru/jour/article/view/1501</self-uri><abstract><p>Введение. Цель статьи состоит в определении и сопоставлении лингвистических характеристик коротких русскоязычных текстов разных жанров, сгенерированных в языковых нейросетях GigaChat, ChatGPT Марти и Яндекс Алиса. Актуальность исследования состоит в том, что изучение лингвистических характеристик сгенерированных текстов позволило сделать выводы о таких характеристиках названных языковых нейросетей, как способность к построению микротестов по заданным в промпте семантическим параметрам, способность избирать контекстуально релевантные значения слов в тематическом наборе дефиниций, способность к построению текста критической интерпретации высказывания. Материалы и методы. В качестве материала исследования избраны порожденные названными выше нейросетями языковые выражения и короткие тексты разной функциональной принадлежности – от предложения и семантической дефиниции слова до текста-обоснования собственного ответа нейросети. В качестве основных использовались метод макроструктурного анализа, метод лексико-семантического анализа, метод грамматического анализа, метод стилистического анализа, метод семантико-прагматического анализа. Анализ. Исследование проводилось по следующему плану: 1) анализ сгенерированных дефиниций слов и предложений, построенных нейросетями из этих дефиниций, 2) анализ сгенерированных контекстуальных дефиниций, 3) анализ сгенерированных коротких текстов на предмет их функционально-семантической адекватности.Результаты. Работа с тематически связанными дефинициями, сгенерированными названными нейросетями, позволила установить, что данные языковые модели в состоянии согласовывать определения слов с контекстом, не являющимся собственно текстом, то есть могут без специального задания в промте, но исходя из перечня слов в нём, определять тему и давать дефиниции по этой теме. В ходе изучения способности языковых нейросетей давать оценку категориальной и референциальной достоверности высказываний установлено, что все три нейросети оказались в состоянии дать правильные мотивированные ответы, за одним исключением, когда нейросеть указала нехватку информации. В ходе изучения текстов, сгенерированных названными языковыми нейросетями, были выявлены пять основных типов нарушений (дефектов) в них, которые могут квалифицироваться как типичные для этих нейросетей: 1) нарушения логико-семантических связей в тексте, выполнение ложных семантических операций; 2) нарушения бытийных прагматических пресуппозиций (знания о мире, о свойствах предметов); 3) нарушения коммуникативно-прагматических правил речевого поведения; 4) грамматические отклонения в управлении и согласовании; 5) макроструктурные нарушения.</p></abstract><trans-abstract xml:lang="en"><p>Introduction. The purpose of the article is to determine and compare the linguistic characteristics of short Russian-language texts of different genres generated in the language neural networks GigaChat, ChatGPT Marty and Yandex Alice. The relevance of the study is that the study of the linguistic characteristics of the generated texts allowed us to draw conclusions about such characteristics of the named language neural networks as the ability to build microtests based on the semantic parameters specified in the prompt, the ability to select contextually relevant meanings of words in a thematic set of definitions and the ability to build a text of critical interpretation of the statement.Materials and Methods. The material for the study was linguistic expressions and short texts of different functional affiliation generated by the above-mentioned neural networks – from a sentence and a semantic definition of a word to a text produced by the neural network itself. The following methods were used as the main ones: macrostructural analysis, lexical-semantic analysis, grammatical analysis, stylistic analysis and semanticpragmatic analysis.Analysis. The study was conducted according to the following plan: 1) analysis of generated definitions of words and sentences constructed by neural networks from these definitions, 2) analysis of generated contextual definitions, 3) analysis of generated texts for their functional-semantic adequacy.  Results. Working with thematically related definitions generated by the above-mentioned neural networks made it possible to establish that these language models are able to coordinate definitions of words with a context that is not the text itself, that is, they can, without a special assignment in the prompt, but based on the list of words in it, determine the topic and give definitions on this topic. In the course of studying the ability of language neural networks to assess the categorical and referential reliability of statements, it was found that all three neural networks were able to give correct motivated answers, with one exception, when the neural network indicated a lack of information. In the course of studying the texts generated by the named language neural networks, five main types of violations (defects) were identified in them, which can be qualified as typical for these neural networks: 1) violations of logical-semantic connections in the text, the implementation of false semantic operations; 2) violations of existential pragmatic presuppositions (knowledge about the world, about the properties of objects); 3) violations of communicativepragmatic rules of speech behavior; 4) grammatical deviations; 5) macrostructural violations.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>текст</kwd><kwd>генеративный</kwd><kwd>языковая нейросеть</kwd><kwd>семантический</kwd><kwd>прагматический</kwd><kwd>дефект</kwd><kwd>галлюцинация</kwd></kwd-group><kwd-group xml:lang="en"><kwd>text</kwd><kwd>generative</kwd><kwd>language neural network</kwd><kwd>semantic</kwd><kwd>pragmatic</kwd><kwd>defect</kwd><kwd>hallucination</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">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 р. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Грайс Г. П. Логика и речевое общение // Новое в зарубежной лингвистике: Лингвистическая прагматика. Вып. XVI. М.: Прогресс, 1985. С. 217–237.</mixed-citation><mixed-citation xml:lang="en">Grice GP. Logics and conversation in New in foreign linguistics: Linguistic pragmatics. Issue XVI. Moscow: Progress; 1985. P. 217-237.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Гусаренко С. В. Дефекты когнитивно-семантических структур как причина высокой энтропии актуального дискурса // Известия Южного федерального университета. Филологические науки. 2009. №2. С. 68–74.</mixed-citation><mixed-citation xml:lang="en">Gusarenko SV. Defects of cognitive-semantic structures as a cause of high entropy of current discourse. Izvestija Juzhnogo federal'nogo universiteta. Filologicheskie nauki. 2009;(2):68-74. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</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. Novoe v zarubezhnoi lingvistike: Kognitivnye aspekty yazyka. 1988;XXIII:153-211. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Столнейкер Р. Прагматика // Новое в зарубежной лингвистике: Лингвистическая прагматика. Вып. XVI. 1985. С. 419–438.</mixed-citation><mixed-citation xml:lang="en">Stolneiker R. Pragmatics. Novoe v zarubezhnoi lingvistike: Lingvisticheskaya pragmatika. 1985;XVI:419-438. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Цвигун Т. В., Черняков А. Н. Хармс vs НейроХармс: нейросеть как лаборатория нарратива // Новый филологический вестник. 2023. № 4. С. 80-92.</mixed-citation><mixed-citation xml:lang="en">Tsvigun TV, Chernyakov AN. Harms vs. NeuroHarms: neural network as a narrative laboratory. Novyj filologicheskij vestnik. 2023;(4):80-92. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Яндекс Алиса. URL: https://a.ya.ru/ (дата обращения: 15.02.2024).</mixed-citation><mixed-citation xml:lang="en">Yandex Alice. URL: https://a.ya.ru/ (accessed: 15.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">ChatGPT Марти. URL: https://web.telegram.org/a/#6139209801 (accessed: 15.02.2024).</mixed-citation><mixed-citation xml:lang="en">ChatGPT. URL: https://web.telegram.org/a/#6139209801 (accessed: 15.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">GigaChat. URL: https://web.telegram.org/a/#6218783903 (accessed: 15.02.2024).</mixed-citation><mixed-citation xml:lang="en">GigaChatPro. URL: https://web.telegram.org/a/#6218783903 (accessed: 15.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Luo J., Xiao C., Ma F. Zero-Resource Hallucination Prevention for Large Language Models. URL: https://www.researchgate.net/publication/373715030_Zero-Resource_Hallucination_Prevention_for_Large _Language_Models. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Luo J, Xiao C, Ma F. Zero-Resource Hallucination Prevention for Large Language Models. URL: https://www.researchgate.net/publication/373715030_Zero-Resource_Hallucination_Prevention_for_ Large_Language_Models (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Lipkin B.,Wong L.,Grand G.,Tenenbaum J. B. Evaluating statistical language models as pragmatic reasoners. URL: https://www.researchgate.net/publication/370469496_Evaluating_statistical_language_models_as_pragmatic_reasoners. (accessed: 26.02.2024)</mixed-citation><mixed-citation xml:lang="en">Lipkin B, Wong L, Grand G, Tenenbaum JB. Evaluating statistical language models as pragmatic reasoners. URL: https://www.researchgate.net/publication/370469496_Evaluating_statistical_language_models_as_pragmatic_reasoners (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">McKenna N., Li T., Cheng L., Hosseini M.J., Johnson M., Steedman M. Sources of Hallucination by Large Language Models on Inference Tasks. URL: https://www.researchgate.net/publication/371009111_Sources_of_Hallucination_by_Large_Language_Models_on_Inference_Tasks. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">McKenna N, Li T, Cheng L, Hosseini MJ, Johnson M, Steedman M. Sources of Hallucination by Large Language Models on Inference Tasks. URL: https://www.researchgate.net/publication/371009111_Sources_of_Hallucination_by_Large_Language_Models_on_Inference_Tasks (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Margolina А., Kolmogorova А. Exploring Evaluation Techniques in Controlled Text Generation: A Comparative Study of Semantics and Sentiment in ruGPT3large-Generated and Human-Written Movie Reviews // Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2023” (Moscow, June 14–17, 2023). URL: https://www.dialog-21.ru/media/5874/margolinaapluskolmogorovaa052.pdf. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Margolina А, Kolmogorova А. Exploring Evaluation Techniques in Controlled Text Generation: A Comparative Study of Semantics and Sentiment in ruGPT3large-Generated and Human-Written Movie Reviews. Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2023” (Moscow, June 14–17, 2023). URL: https://www.dialog-21.ru/media/5874/margolinaapluskolmogorovaa052.pdf (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Oluwaseyi J, Odu A. Exploring models that learn the structure and semantics of language to generate coherent text. URL: https://www.researchgate.net/publication/377111766_Exploring_models_that_learn_the_structure_and_semantics_of_language_to_generate_coherent_text_Author. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Oluwaseyi J, Odu A. Exploring models that learn the structure and semantics of language to generate coherent text. URL: https://www.researchgate.net/publication/377111766_Exploring_models_that_learn_the_structure_and_semantics_of_language_to_generate_coherent_text_Author (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Rawte V., Priya P., Tonmoy S. M. T. Zaman S. M. M., Chadha A., Sheth A., Das A. "Sorry, Come Again?" Prompting - Enhancing Comprehension and Diminishing Hallucination with [PAUSE] -injected Optimal Paraphrasing. URL: https://www.researchgate.net/publication/379372849_Sorry_Come_Again_Prompting_-Enhancing_Comprehension_and_Diminishing_Hallucination_ with_PAUSE_-injected_Optimal_Paraphrasing. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Rawte V, Priya P, Tonmoy SMТ, Zaman SMM, Chadha A, Sheth A, Das A. "Sorry, Come Again?" Prompting -Enhancing Comprehension and Diminishing Hallucination with [PAUSE] -injected Optimal Paraphrasing. URL: https://www.researchgate.net/publication/379372849_Sorry_Come_ Again_Prompting_-Enhancing_Comprehension_and_Diminishing_ Hallucination_ with_PAUSE_-injected_Optimal_Paraphrasing (accessed: 26.02.2024)</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Stoyanova Berbatova M., Salambashev Y., Evaluating Hallucinations in Large Language Models for Bulgarian Language. URL: https://www.researchgate.net/publication/373894930_Evaluating_Hallucinations_in_Large_Language_Models_for_Bulgarian_Language. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Stoyanova Berbatova M, Salambashev Y, Evaluating Hallucinations in Large Language Models for Bulgarian Language URL: https://www.researchgate.net/publication/373894930_Evaluating_Hallucinations_in_Large_Language_Models_for_Bulgarian_Language (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Tang R., Chuang Y.N., Hu X. The Science of Detecting LLM-Generated Texts. URL: https://www.researchgate.net/publication/368684822_The_Science _of_Detecting_LLM-Generated_Texts. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Tang R, Chuang YN, Hu X. The Science of Detecting LLM-Generated Texts. URL: https://www.researchgate.net/publication/368684822_The_Science_ of_Detecting_LLM-Generated_Texts (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Turganbay R., Surkov V., Evseev D., Drobyshevskiy M. Generative Question Answering Systems over Knowledge Graphs and Text. URL: https://www.dialog-21.ru/media/5878/turganbayrplusetal043.pdf. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Turganbay R, Surkov V, Evseev D, Drobyshevskiy M. Generative Question Answering Systems over Knowledge Graphs and Text. URL: URL:https://www.dialog-21.ru/media/5878/turganbayrplusetal043.pdf (accessed: 26.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang Y., Li Y., Cui L., Cai D. Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models. URL: https://www.researchgate.net/publication/373686208_Siren's_Song_in_the_AI_Ocean_A_Survey_on_Hallucination_in_Large_Language_Models. (accessed: 26.02.2024).</mixed-citation><mixed-citation xml:lang="en">Zhang Y, Li Y, Cui L, Cai D. Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models. URL: https://www.researchgate.net/publication/373686208_Siren's_Song_in_the_AI_Ocean_A_Survey_on_Hallucination_in_Large_Language_Models (accessed: 15.02.2024).</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>
