THE CATEGORIAL-PRAGMATIC NATURE OF INSTRUCTIONAL DISCOURSE IN COMMUNICATION WITH AN ALGORITHMIC ADDRESSEE
Keywords:
instructional discourse; algorithmic addressee; prompt; directive speech act; pragmatics; conversational grounding; repair; human-LLM interactionAbstract
The rapid spread of large language model interfaces has transformed natural-language instruction from a primarily human-directed discourse practice into a mode of communication addressed to a computational system. This change creates a theoretical problem for linguistics: the discourse retains recognizable directive, procedural, interpersonal, and repair-related properties, yet its addressee cannot be treated as a human interlocutor with embodied experience, socially accountable intentions, or independently established common ground. The present study develops an integrative linguistic account of this emerging configuration. It asks which categorial-pragmatic properties define instructional discourse, how those properties are reorganized when an instruction is directed to an algorithmic addressee, and how grounding and repair shape multi-turn interaction. A purposive corpus of 32 foundational and recent studies in discourse analysis, speech-act theory, procedural communication, human-machine communication, prompt research, conversational grounding, and repair was subjected to deductive-inductive conceptual coding. The synthesis yielded a nine-category model comprising task-intent orientation, directive and deontic force, referential anchoring, contextual and audience specification, procedural sequencing, constraint architecture, output and quality specification, interpersonal calibration, and metadiscursive monitoring and repair. The findings further identify five pressures characteristic of algorithmically addressed instruction: explicitization, modularization, formalizability, asymmetrical grounding, and output-contingent revision. On this basis, a prompt is defined as an instructional macroact whose component microacts regulate not only what is to be done but also the object, conditions, limits, form, and revision of the expected output. The term algorithmic addressee is proposed as a functional discourse role rather than an attribution of consciousness or human-like understanding. The model clarifies the linguistic status of prompts, distinguishes repair from optional refinement, and provides an analytical framework for future corpus-based comparison of instructional discourse across languages.
References
1.Austin, J. L. (1962). How to do things with words. Clarendon Press.
2.Bender, E. M., & Koller, A. (2020). Climbing towards NLU: On meaning, form, and understanding in the age of data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 5185-5198). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.463
3.Brown, P., & Levinson, S. C. (1987). Politeness: Some universals in language usage. Cambridge University Press.
4.Clark, H. H. (1996). Using language. Cambridge University Press.
5.Clark, H. H., & Brennan, S. E. (1991). Grounding in communication. In L. B. Resnick, J. M. Levine, & S. D. Teasley (Eds.), Perspectives on socially shared cognition (pp. 127-149). American Psychological Association. https://doi.org/10.1037/10096-006
6.Clark, H. H., & Schaefer, E. F. (1989). Contributing to discourse. Cognitive Science, 13(2), 259-294. https://doi.org/10.1207/s15516709cog1302_7
7.Elizabeth, M., Lecorvé, G., Rojas Barahona, L. M., & Ochs, M. (2026). Conversational grounding in large language models: Evaluation methods, challenges and future directions. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue (pp. 151-163). Association for Computational Linguistics.
8.Esposito, E. (2022). Artificial communication: How algorithms produce social intelligence. MIT Press.
9.Farkas, D. K. (1999). The logical and rhetorical construction of procedural discourse. Technical Communication, 46(1), 42-54.
10.Grice, H. P. (1975). Logic and conversation. In P. Cole & J. L. Morgan (Eds.), Syntax and semantics: Vol. 3. Speech acts (pp. 41-58). Academic Press.
11.Guzman, A. L., & Lewis, S. C. (2020). Artificial intelligence and communication: A human-machine communication research agenda. New Media & Society, 22(1), 70-86. https://doi.org/10.1177/1461444819858691
12.Hancock, J. T., Naaman, M., & Levy, K. (2020). AI-mediated communication: Definition, research agenda, and ethical considerations. Journal of Computer-Mediated Communication, 25(1), 89-100. https://doi.org/10.1093/jcmc/zmz022
13.Herring, S. C. (2004). Computer-mediated discourse analysis: An approach to researching online behavior. In S. A. Barab, R. Kling, & J. H. Gray (Eds.), Designing for virtual communities in the service of learning (pp. 338-376). Cambridge University Press. https://doi.org/10.1017/CBO9780511805080.016
14.Herring, S. C. (2013). Discourse in Web 2.0: Familiar, reconfigured, and emergent. In D. Tannen & A. M. Trester (Eds.), Discourse 2.0: Language and new media (pp. 1-25). Georgetown University Press.
15.Hohenstein, J., Kizilcec, R. F., DiFranzo, D., Aghajari, Z., Mieczkowski, H., Levy, K., Naaman, M., Hancock, J. T., & Jung, M. F. (2023). Artificial intelligence in communication impacts language and social relationships. Scientific Reports, 13, Article 5487. https://doi.org/10.1038/s41598-023-30938-9
16.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
17.Longacre, R. E. (1996). The grammar of discourse (2nd ed.). Plenum Press.
18.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
19.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), 1-27. https://doi.org/10.1145/3731756
20.Madge, C., Purver, M., & Poesio, M. (2025). Referential ambiguity and clarification requests: Comparing human and LLM behaviour. In Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference (pp. 1-11). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.crac-1.1