Cognitive Modeling of Ethnocultural Units with Somatic Components in AI Systems and Semantic Deviations in Translation

The article is devoted to a pressing issue in modern computational linguistics and NLP – investigating the ability of Large Language Models (LLMs) to recognize ethnocultural codes and national worldview layers in the Kazakh language. The relevance of this study is driven by the fact that the primary limitation in current AI-based translation systems lies in their inability to correctly identify ethnocultural units, combined with a scarcity of research in this field and a growing demand for AI models adapted to translation erratology capable of accurately conveying cultural meanings. The purpose of the study is to identify the cognitive mechanisms underlying the processing of Kazakh somatic ethnographisms (zhürek zhalgau, bauyrymdau, auzyna tükirtu, etc.) across ChatGPT, Gemini, and Claude systems, as well as to classify semantic deviations (aberrations) in the digital environment. The study employs a set of methods, including cognitive modeling, linguocultural analysis, and comparative-experimental techniques. The empirical base comprises somatic ethnounits extracted from the classical literary works of A. Kekilbayev, M. Auezov, T. Alimkulov, and T. Akhtanov. To test the models' context sensitivity, two-stage (lexical and context-pragmatic) linguistic prompts were developed. The experimental analysis results demonstrated that AI systems are frequently prone to errors such as “pragmatic inversion,” “linguocultural deritualization,” and “denotative literalism” when interpreting Kazakh ethnosomatic codes. The models exhibited phenomena of replacing sacred meanings with Western ethical norms and cognitive inertia. The value of the study lies in its being the first to examine the ethnocultural maladaptation of generative applications (ChatGPT, Gemini, Claude) from a cognitive-semantic perspective using Kazakh language material. The research findings possess practical significance for the specialized fine-tuning of AI models using the Kazakh language's ethnographic database and for improving machine translation quality.

1. Abdrahmanova, M.B (2008) “Koz” koncepti: lingvomadeni zhane tanymdyq paradigmasi: filol. gyl. kand. dis. Almaty. [Abdrakhmanova, M.B (2008) The “Eye” concept: linguocultural and cognitive paradigm: Candidate of Philological Sciences dissertation. Almaty.] (in Kazakh)

2. Aldabergenova, A.A, Zhumabekova, A.K. (2024) Zhanga audarma matinderining balamalylyq denggeji. Toraigyrov universitetining Habarshysy. Filologijalyq serija. No. 3. 44-52-bb. DOI 10.48081/HUHW2781. [Aldabergenova, A.A., Zhumabekova, A.K. (2024) The level of equivalence of new translation texts. Bulletin of Toraighyrov University Philological series. No. 3. Pp. 44-52.] (in Kazakh)

3. Alimzhanova, Sh.A. (2025) The role of somatisms in polysemantic phraseological units: a cognitive and cultural feature. International Journal of Literature and Languages 5(03). Pp. 74-77. DOI 10.37547/ijll/Volume05Issue03-19. (in English)

4. Barmenqulova, A.S., Zhagnabekova, A.A., Mankeeva, Zh.A. (2023) Jetnomadeni birlikterding korpusta berilu zholdary. Tiltanym. No. 1 (56). 56-66-bb. DOI 10.55491/2411-6076-2023-1-56-66. [Barmenkulova, A.S., Zhanabekova, A.A., Mankeyeva, Zh.A. (2023) Ways of transmission of ethnocultural units in the corpus. Tiltanym. No. 1 (56). Pp. 56-66.] (in Kazakh)

5. Bender, E.M., Koller, A. (2020) Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 5185–5198. (in English)

6. Cao, Y., Zhou, L., Lee, S., Cabello, L., Chen, M., Hershcovich, D. (2023) Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). Pp. 53–67. (in English)

7. Eskermesova, G.A., Ermekova, T.N., Shojbekova, G.B. (2026) Jetnomadeni birlikterding zhasandy intellekt arqyly audaryluy: mashinalyq audarmalar zhane onyng sapasyn bagalau. Evrazija gumanitarlyq institutynyng Habarbarysy. No. 2. 67–74-bb. DOI https://doi.org/10.55808/1999-4214.2026-2.06 [Yeskermesova, G.A., Yermekova, T.N., Shoibekova, G.B. (2026) Translation of ethnocultural units through artificial intelligence: machine translation and evaluation of its quality. Bulletin of the Eurasian Humanities Institute. No. 2. Pp. 67–74.] (in Kazakh)

8. Imangazina, M. (2024) Audarmadagi kommunikant jemocijasy: tur-tus ataularynyng qyzmeti men semantikasy. Vestnik Evrazijskogo gumanitarnogo instituta. No. 3. 41-52-bb. [Imangazina, M. (2024) Communicant emotion in translation: functions and semantics of color terms. Bulletin of the Eurasian Humanities Institute. No. 3. Pp. 41-52.] (in Kazakh)

9. Isaeva, G.S., Otebaeva, Je.A., Serikqyzy, M. (2023) Lingvomadeni ishkorpusty azirleudegi madeni-semantikalyq belgilenim. Tiltanym. No. 3 (135). 135-143-bb. DOI 10.55491/2411-6076-2023-3-135-143. [Issayeva, G.S., Utebayeva, E.A., Serikkyzy, M. (2023) Cultural and semantic markup in the development of the linguocultural subcorpus. Tiltanym. No. 3 (135). Pp. 135-143.] (in Kazakh)

10. Islam, A. (2025) Medialingvistika negizderi zhane media audarma maseleleri. Qaragandy universitetining Habarshysy. Filologija serijasy. No. 2 (118). 151–160-bb. [Islam, A. (2025) Fundamentals of medialinguistics and issues of media translation. Bulletin of the Karaganda University Philology series. No. 2 (118). Pp. 151–160.] (in Kazakh)

11. Kadyrbek, N., Tuimebayev, Zh., Mansurova, M., Viegas, V. (2025) The Development of Small-Scale Language Models for Low-Resource Languages, with a Focus on Kazakh and Direct Preference Optimization. Information. 16(1) 85. DOI 10.3390/info16010085. (in English)

12. Karyukin, V., Rakhimova, D., Karibayeva, A. et al (2024) The neural machine translation models for the lowresource Kazakh–English language pair. Scientific Reports. 14 7166. DOI 10.1038/s41598-024-57854-x. (in English)

13. Mankeeva, Zh. (2014) Qazaq til bilimining maseleleri. Almaty: “Abzal-Ai” baspasy. 640 b. [Mankeyeva, Zh. (2014) Issues of Kazakh linguistics. Almaty: “Abzal-Ai” publishing house. 640 p.] (in Kazakh)

14. Marcus, G. (2020) The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence. arXiv preprint arXiv:2002.06177. Pp. 1-45. (in English)

15. Maxutov, A., Myrzakhmet, A., Braslavski, P. (2024) Do LLMs Speak Kazakh? A Pilot Evaluation of Seven Models. Proceedings of EMNLP. Pp. 112–128. (in English)

16. Nurzhanova, A. (2010) Duniening qarabajyr bejnesi: frazeologijalyq fragmentting somatikalyq kody: kand. dis. Astana. [Nurzhanova, A. (2010) Primitive picture of the world: somatic code of the phraseological fragment: Candidate dissertation. Astana.] (in Kazakh)

17. Qajdar, A. (2009) Qazaqtar ana tili aleminde (jetnolingvistikalyq sozdik). T. 1: Adam. Almaty Dajk-Press. 784 b. [Kaidar, A. (2009) Kazakhs in the world of their native language (ethnolinguistic dictionary). Vol 1: Man. Almaty: Dyke press. 784 p.] (in Kazakh)

18. Qazaq adebi tilining sozdigi. On bes tomdyq. 6 tom (2011a) Almaty, 752 b. [Dictionary of the Kazakh literary language. In fifteen volumes. Vol. 6. (2011a) Almaty, 752 p.] (in Kazakh)

19. Qazaq adebi tilining sozdigi. On bes tomdyq. 10 tom. (2011b) Almaty, 752 b. [Dictionary of the Kazakh literary language In fifteen volumes. Vol. 10 (2011b) Almaty, 752 p.] (in Kazakh)

20. Qazaqtyng jetnografijalyq kategorijalar, ugymdar men ataularynyng dasturli zhujesi. T. 1. A-D (2011) Almaty: DPS. 735 b. [Traditional system of Kazakh ethnographic categories concepts and names. Vol. 1. A-D (2011) Almaty: DPS. 735 p.] (in Kazakh)

21. Ramanova, A.A. (2023) Qazaq tilindegi somatizmderding leksikalyq-semantikalyq orisi. Batys Qazaqstan innovacijalyq-tehnologijalyq universitetining Habarshysy. T. 68. No. 1. 101-110-bb. DOI 10.48371/PHILS.2023.23.18.011. [Ramanova, A.A. (2023) Lexical and semantic field of somatisms in the Kazakh language. Bulletin of the West Kazakhstan Innovation and Technology University. Vol. 68. No. 1. Pp. 101-110.] (in Kazakh)

22. Smagulova, G. (2020) Qazaq frazeologijasy lingvistikalyq paradigmalarda: monografija. Almaty: “Eltanym baspasy”. 256 b. [Smagulova, G. (2020) Kazakh phraseology in linguistic paradigms: monograph. Almaty: “Eltanym publishing house”. 256 p.] (in Kazakh)

23. Syzdyq, R. (2025) Gylymi tanym uzikteri: Maqalalar zhinagy. 1-kitap. Almaty: “Sardar”. Qazaq zhane orys tilderinde. [Syzdyk, R. (2025) Fragments of scientific knowledge: Collection of articles. Book 1. Almaty: “Sardar”. In Kazakh and Russian languages.] (in Kazakh)

24. Tashauov, A.S. (1995) “Kodeks Kumanikus” tilindegi somatikalyq ataular zhane olardyng leksika-semantikalyq toptary: filol. gyl. kand. dis. Almaty. 161 b. [Tashauov, A.S. (1995) Somatic names in “Codex Cumanicus” and their lexicalsemantic groups: Candidate of Philological Sciences dissertation. Almaty. 161 p.] (in Kazakh)

25. Tekgürler, M. (2025) LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models. Proceedings of LaTeCH-CLfL. Pp. 227–237. (in English)

26. Togmanov, M., Mukhituly, N., Turmakhan, D. et al (2025) KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan. MBZUAI Technical Report. Pp. 1-22. (in English)

27. Toleu, A., Tolegen, G., Ualiyeva, I. (2024) Fine-Tuning Large Language Models for Kazakh Text Simplification // Applied Sciences. Vol. 14(5). Art. No. 2100. (in English)

28. Uali, N. (2021) Qazaq soz madenietining teorijalyq negizderi. Monografija. Almaty: Qazaq tili baspasy. 424 b. [Uali, N. (2021) Theoretical foundations of Kazakh speech culture. Monograph. Almaty: Qazaq tili publishing house. 424 p.] (in Kazakh)

29. Uyzbaeva, B.K. (1994) Qazaq tilindegi somatikalyq etistik frazeologizmderding jetnolingvistikalyq sipaty: filol. gyl. kand. dis. Almaty. [Uyzbayeva, B.K. (1994) Ethnolinguistic nature of somatic verbal phraseologisms in the Kazakh language: Candidate of Philological Sciences dissertation. Almaty.] (in Kazakh)

30. Wang, X., Fantinuoli, C. (2024) Exploring the Correlation between Human and Machine Evaluation of Simultaneous Speech Translation // Proceedings of the 25th Annual conference of the European Association for Machine Translation. Vol. 1. Pp. 327–336. (in English)

31. Zhanabekova, A.A., Usenov, M., Tlegenova, G.B. (2026) Sozdanie bol`shih jazykovyh modelej v kazahstanskom jazyke: kazahstanskij opyt i global`nye trendy. Tiltanym. No. 1. S. 135–149. DOI https://doi.org/10.55491/2411-6076-2026-1-135-149. [Zhanabekova, A.A., Usenov, M., Tlegenova, G.B. (2026) Creation of large language models in the Kazakh language: Kazakhstani experience and global trends. Tiltanym. No. 1. Pp. 135–149.] (in Russian)