Prompts have become a primary linguistic interface through which users formulate intentions, specify tasks, and regulate the outputs of large language models. Existing research has generated extensive taxonomies of prompting techniques, yet it often classifies prompts by computational strategy or performance effect rather than by their internal linguistic architecture. This study develops a structural-compositional account of prompts as instructional macroacts in human-AI discourse. A purposive integrative review of 22 foundational and contemporary sources published between 1962 and 2026 was conducted. The sources were coded at three levels: macrostructural organization, semantic-pragmatic composition, and surface realization. The synthesis identifies ten recurrent functional slots: role, goal, task, input/object, context, audience, constraint, demonstration, output format, and verification. These slots combine into seven major structural models ranging from the minimal directive model to task-object, goal-conditioned, constraint-augmented, role-contextualized, demonstration-guided, hierarchical-decomposed, and iterative-dialogic configurations. The findings show that prompt complexity cannot be reduced to word count. It is determined by slot breadth, relational depth, explicitness, and extension across conversational turns. The proposed Prompt Structural-Composition Framework distinguishes the communicative content of a prompt from the linguistic relations that organize it and provides a common analytic basis for comparing prompts across languages. The model is particularly applicable to future English-Uzbek studies because it allows functionally equivalent components to be compared even when their morphological and syntactic realization differs.
From Minimal Directives to Layered Instructional Frames: Structural-Compositional Models of Prompts in Human-Ai Discourse
DOI:
Keywords:
Abstract
Downloads
References
Austin, J. L. (1962). How to do things with words. Clarendon Press.
Farkas, D. K. (1999). The logical and rhetorical construction of procedural discourse. Technical Communication, 46(1), 42-54.
Halliday, M. A. K., & Matthiessen, C. M. I. M. (2014). Halliday's introduction to functional grammar (4th ed.). Routledge.
Hewing, M., & Leinhos, V. (2024). The Prompt Canvas: A literature-based practitioner guide for creating effective prompts in large language models. arXiv. https://doi.org/10.48550/arXiv.2412.05127
Jeoung, S., Chen, Y., Zhang, Y., Wang, S., Ding, H., & Cheong, L. L. (2026). PromptPrism: A linguistically-inspired taxonomy for prompts. In Findings of the Association for Computational Linguistics: EACL 2026 (pp. 1168-1192). Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.findings-eacl.61
Karmaker, S. K., & Feng, D. (2023). TELeR: A general taxonomy of LLM prompts for benchmarking complex tasks. In Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 14197-14203). Association for Computational Linguistics.
Khot, T., Trivedi, H., Finlayson, M., Fu, Y., Richardson, K., Clark, P., & Sabharwal, A. (2023). Decomposed prompting: A modular approach for solving complex tasks. In The Eleventh International Conference on Learning Representations.
Liang, J. T., Lin, M., Rao, N., & Myers, B. (2025). Prompts are programs too! Understanding how developers build software containing prompts. Proceedings of the ACM on Software Engineering, 2(FSE), Article FSE072. https://doi.org/10.1145/3729342
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9), 1-35. https://doi.org/10.1145/3560815
Longacre, R. E. (1996). The grammar of discourse (2nd ed.). Plenum Press.
Lu, A., Zhang, H., Zhang, Y., Wang, X., & Yang, D. (2023). Bounding the capabilities of large language models in open text generation with prompt constraints. In Findings of the Association for Computational Linguistics: EACL 2023 (pp. 1982-2008). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-eacl.148
Ma, Q., Peng, W., Yang, C., Shen, H., Koedinger, K., & Wu, T. (2025). What should we engineer in prompts? Training humans in requirement-driven LLM use. ACM Transactions on Computer-Human Interaction, 32(4), Article 41, 1-27. https://doi.org/10.1145/3731756
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730-27744.
Reynolds, L., & McDonell, K. (2021). Prompt programming for large language models: Beyond the few-shot paradigm. In Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems (pp. 1-7). Association for Computing Machinery. https://doi.org/10.1145/3411763.3451760
Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., et al. (2024). The Prompt Report: A systematic survey of prompting techniques. arXiv. https://doi.org/10.48550/arXiv.2406.06608
Searle, J. R. (1969). Speech acts: An essay in the philosophy of language. Cambridge University Press.
Searle, J. R. (1976). A classification of illocutionary acts. Language in Society, 5(1), 1-23. https://doi.org/10.1017/S0047404500006837
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E. H., Le, Q. V., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824-24837.
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023). A prompt pattern catalog to enhance prompt engineering with ChatGPT. arXiv. https://doi.org/10.48550/arXiv.2302.11382
Zamfirescu-Pereira, J. D., Wong, R. Y., Hartmann, B., & Yang, Q. (2023). Why Johnny can't prompt: How non-AI experts try (and fail) to design LLM prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Article 437, pp. 1-21). Association for Computing Machinery. https://doi.org/10.1145/3544548.3581388
Zhou, Y., Muresanu, A. I., Han, Z., Paster, K., Pitis, S., Chan, H., & Ba, J. (2023). Large language models are human-level prompt engineers. In The Eleventh International Conference on Learning Representations.
Zi, Y., Menon, H., & Guha, A. (2025). More than a score: Probing the impact of prompt specificity on LLM code generation. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (pp. 2380-2402). Association for Computational Linguistics.