--- title: "Pragmatics beyond humans: meaning, communication, and LLMs" description: "As a replacement, the paper proposes the Human-Machine Communication (HMC) framework. 6 references." authors: ["Vit Gvo\\vzdiak"] year: 2025 venue: "arXiv:2508.06167" source: "https://arxiv.org/abs/2508.06167" doi: "10.46938/tv.2026.686" arxiv: "2508.06167" licence: "CC BY 4.0 (arXiv)" licence_url: "http://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/gvo-vzdiak-2025-pragmatics-humans-meaning-communication-llms/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gvo-vzdiak-2025-pragmatics-humans-meaning-communication-llms/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/13/) / Pragmatics beyond humans: meaning, communication, and LLMs # Pragmatics beyond humans: meaning, communication, and LLMs **Authors:** Vit Gvo\\vzdiak · **Year:** 2025 · **Venue:** arXiv:2508.06167 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://doi.org/10.46938/tv.2026.686) · [PDF](https://arxiv.org/pdf/2508.06167) · [DOI 10.46938/tv.2026.686](https://doi.org/10.46938/tv.2026.686) · [arXiv 2508.06167](https://arxiv.org/abs/2508.06167) · [OpenAlex](https://openalex.org/W4415193070) **Citations:** 2 citations (OpenAlex, 2026-10-14) ## Summary This is a theoretical essay, not an empirical study. It uses no dataset, model training, or benchmark. Instead, it asks how pragmatic theory should change now that LLMs take part in everyday communication. The author argues against the classic Morris/Carnap layering, where syntax comes first, semantics sits on it, and pragmatics is a leftover top layer. That layering makes it too easy to deny LLMs any competence: if they lack syntax or semantics, they cannot have pragmatics either. As a replacement, the paper proposes the Human-Machine Communication (HMC) framework. The essay then makes three further moves: - It contends that Gricean, human-centred pragmatics fits predictive systems poorly. The probabilistic Rational Speech Act approach matches them better, because it frames meaning as optimisation rather than truth evaluation. - It names three kinds of "substitutionalism" that bias how LLMs are evaluated. - It introduces "context frustration": ever-larger context windows coincide with a breakdown of shared context, which pushes users to spell out context explicitly. The work matters because it questions the theoretical assumptions behind many pragmatic benchmarks for LLMs. ## Key points - The paper targets the semiotic trichotomy (syntax, then semantics, then pragmatics). It also discusses arguments that rely on that hierarchy: Searle's Chinese Room, Bender and Koller's Octopus Test, the National Library of Thailand thought experiment, and Moro et al.'s claim about possible versus impossible languages. - A footnote cites Kallini et al. (ACL 2024). In that study, GPT-2 trained on "impossible" languages performed clearly worse than when trained on English, which partly undercuts Moro et al.'s claim. - The essay recommends the Rational Speech Act framework from probabilistic pragmatics over Gricean models, because LLMs optimise distributional probability rather than evaluate truth. - Substitutionalism comes in three forms: - **Generalising:** one model's behaviour is taken to stand for all LLMs. - **Linguistic:** English is taken to stand for language in general. - **Communicative:** LLMs replace human participants in experimental designs. - "Context frustration" is defined using the Lewisian notion of defective, non-shared context. It arises from many-to-many prompt–reply–re-prompt loops in which users co-construct pragmatic conditions for the model and for themselves. ## Interesting ideas - The paper treats pragmatic interpretation as probabilistic optimisation over what a rational speaker would likely say, in the style of RSA, rather than as checking against truth conditions. - Communicative substitutionalism warns that letting a model stand in for human participants quietly imports anthropomorphic criteria into an evaluation. - Generalising substitutionalism shows that one system's results get read as true of a whole class of systems. - The cited impossible-language experiment shows how text built on linear, non-hierarchical rules can expose whether a learner actually depends on structure. - Context frustration distinguishes context that is explicitly supplied from context that is truly shared, and shows that piling on more input does not close that gap. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (frames): implicature in crate prag could rank candidate readings against an explicit set of alternative utterances, with each alternative's score visible so the inference stays explainable. - **I2** (learn): labels from LLM teacher tiers should be tagged by source and never silently counted as human gold. A human-checked slice should stay separate for final scoring. - **I3** (learn): when silver data comes from several witness parsers, report agreement and errors per witness rather than as one pooled "parser quality" figure. - **I4** (learn): synthetic impossible-language or linearly scrambled inputs could serve as negative controls, showing whether parser and frame scores drop as they should when hierarchy is destroyed. - **I5** (world): the world of a text could mark each fact as stated, inferred, or presupposed-but-missing, so readers can see which background assumptions an answer silently depends on. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions Also on the byline: [Czech Academy of Sciences, Institute of Philosophy](https://ror.org/01hyg6578). 📚 Shelves (3): [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤔 Philosophy](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/philosophy/) · 284 works 🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works ## Cite Cite as: Vit Gvo\\vzdiak. 2025. Pragmatics beyond humans: meaning, communication, and LLMs. arXiv:2508.06167. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{gvovzdiak2025pragmatics, title = {{Pragmatics beyond humans: meaning, communication, and LLMs}}, author = {Vit Gvovzdiak}, year = {2025}, doi = {10.46938/tv.2026.686}, eprint = {2508.06167}, archivePrefix = {arXiv}, url = {https://doi.org/10.46938/tv.2026.686} } ``` - [← previous Pragmatic uses of I don't know, boosters, and hedges in text and talk](https://md.research.elamur.ai/free/en/papers/nguyen-2025-pragmatic-uses-i-don-t/) - [next → Prompt Engineering Techniques for Context-dependent Text-to-SQL in Arabic](https://md.research.elamur.ai/free/en/papers/almohaimeed-2025-prompt-engineering-techniques-context-dependent/) - [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/13/) ## References 6 references, 5 of them with a card of ours. ↗ leads to the work. 1. Andersson, Marta and Dan McIntyre. “Can ChatGPT recognize impoliteness? An exploratory study of the pragmatic awareness of a large language model.” Journal of Pragmatics 239 (2025): 16-36. https://doi.org/10.1016/j.pragma.2025.02.001 Androutsopoulos, Jannis. “Languaging when contexts collapse: Audience design in social networking.” Discourse, Context and Media 4–5 (2014): 62–73. https://doi.org/10.1016/j.dcm.2014.08.006 Baroni, Marco. “On the proper role of linguistically-oriented deep net analysis in linguistic theorizing.” In Algebraic systems and the representation of linguistic knowledge, edited by Shalom Lappin, 5–22. Abingdon-on-Thames: Taylor and Francis, 2022. Basile, Pierpaolo et al. “Exploring the Word Sense Disambiguation Capabilities of Large Language Models.” arXiv:2503.08662 [cs.CL], 2025. https://doi.org/10.48550/arXiv.2503.08662 Bender, Emily and Batya Friedman. “Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science.” Transactions of the Association for Computational Linguistics 6 (2018): 587–604. https://doi.org/10.1162/tacl_a_00041 Bender, Emily. “The #BenderRule: On Naming the Languages We Study and Why It Matters.” The Gradient. Article published September 19, 2019. https://thegradient.pub/the-benderrule-on-naming-the-languages-we-study-and-why-it-matters/. Bender, Emily. “Thought experiment in the National Library of Thailand.” Medium. Article published May 25, 2023. https://medium.com/@emilymenonbender/thought-experiment-in-the-national-library-of-thailand-f2bf761a8a83. Bender, Emily and Alexander Koller. “[Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data](https://md.research.elamur.ai/free/en/papers/bender-2020-climbing-nlu-meaning-form-understanding/).” In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, edited by Dan Jurafsky et al., 5185–5198. Online. Association for Computational Linguistics, 2020. https://doi.org/10.18653/v1/2020.acl-main.463 Biletzki, Anat. “Is there a history of pragmatics?” Journal of Pragmatics 25, no. 4 (1996): 455-470. https://doi.org/10.1016/0378-2166(95)00019-4 [↗](https://doi.org/10.1016/j.pragma.2025.02.001) 2. Bojić, Ljubiša, Predrag Kovačević and Milan Čabarkapa. “Does GPT-4 surpass human performance in linguistic pragmatics?“ Humanities and Social Sciences Communications 12, 794 (2025). https://doi.org/10.1057/s41599-025-04912-x Bolei Ma et al. “[Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://md.research.elamur.ai/free/en/papers/ma-2025-pragmatics-era-large-language-models/)”. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che et al., 8679–8696. Vienna: Association for Computational Linguistics, 2025. https://doi.org/10.18653/v1/2025.acl-long.425 Borg, Emma. Minimal Semantics. Oxford: Oxford University Press, 2004. Borg, Emma. Pursuing Meaning. Oxford: Oxford University Press, 2012. Borg, Emma. “LLMs, Turing tests and Chinese rooms: the prospects for meaning in large language models,” Inquiry (2025). https://doi.org/10.1080/0020174X.2024.2446241 boyd, danah. “Social Network Sites as Networked Publics. Affordances, Dynamics, and Implications.” In A Networked Self. Identity, Community, and Culture on Social Networks Sites, edited by Zizi Papacharissi, 39–58. New York – London: Routledge, 2011. Cappelen, Herman and Ernie Lepore. Insensitive Semantics. Malden – Oxford – Carlton: Blackwell, 2005. Cappelen, Herman and Josh Dever. Bad Language. Oxford: Oxford University Press, 2019. Cappelen, Herman and Josh Dever. “AI with Alien Content and Alien Metasemantics.” In The Oxford Handbook of Applied Philosophy of Language, edited by Ernie Lepore and Luvell Anderson, 573–593. Oxford: Oxford University Press, 2024. Carenini, Gaia et al. “Large Language Models Behave (Almost) As Rational Speech Actors: Insights From Metaphor Understanding.” In Open Review / Information-Theoretic Principles in Cognitive Systems Workshop at 37th Conference on Neural Information Processing Systems (NeurIPS 2023), Article published October 27, 2023. https://openreview.net/pdf?id=SosbRhZLBV. Carnap, Rudolf. Introduction to Semantics. Cambridge: Harvard University Press, 1948. Carston, Robyn. Thoughts and Utterances. Oxford – Berlin: Blackwell, 2002. Chen, Xi Jun Li and Yuting Ye. “A feasibility study for the application of AI-generated conversations in pragmatic analysis.” Journal of Pragmatics 223 (2024): 14-30. https://doi.org/10.1016/j.pragma.2024.01.003 Cohn-Gordon, Reuben; Noah D. Goodman and Christopher Potts. “An Incremental Iterated Response Model of Pragmatics.” arXiv:1810.00367 [cs.CL]. 2018. https://doi.org/10.48550/arXiv.1810.00367 Cong, Yan. “Manner implicatures in large language models.” Sci Rep 14, 29113 (2024). https://doi.org/10.1038/s41598-024-80571-3 Degen, Judith. “The Rational Speech Act Framework.” Annual Review of Linguistics 9 (2023): 519– 40. https://doi.org/10.1146/annurev-linguistics-031220-010811 Dentella, Vittoria et al. “Testing AI on language comprehension tasks reveals insensitivity to underlying meaning.” Scientific Reports 14, 28083 (2024). https://doi.org/10.1038/s41598-024-79531-8 Devitt, Michael. Overlooking Conventions. Cham: Springer, 2021. Dietrich, Jürgen and André Hollstein. “Performance and Reproducibility of Large Language Models in Named Entity Recognition: Considerations for the Use in Controlled Environments,” Drug Safety 48 (2025): 287–303. https://doi.org/10.1007/s40264-024-01499-1 Dijk, Bram van et al. “Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding.” In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, edited by Houda Bouamor, Juan Pino, Kalika Bali, 12641–12654. Singapore: Association for Computational Linguistics, 2023. https://doi.org/10.18653/v1/2023.emnlp-main.779 Dynel, Marta. “Lessons in linguistics with ChatGPT: Metapragmatics, metacommunication, metadiscourse and metalanguage in human-AI interactions.” Language & Communication 93 (2023): 107-124. https://doi.org/10.1016/j.langcom.2023.09.002 Erk, Katrin. “The Probabilistic Turn in Semantics and Pragmatics.” Annual Review of Linguistics 8 (2022):101–21. https://doi.org/10.1146/annurev-linguistics-031120-015515 [↗](https://doi.org/10.1057/s41599-025-04912-x) 3. Etzrodt, Katrin et al. “Human-machine-communication: introduction to the special issue.” Publizistik 67 (2022): 439–448. https://doi.org/10.1007/s11616-022-00754-8 Flamino, James et al. “Testing the limits of large language models in debating humans.” Scientific Reports 15, 13852 (2025). https://doi.org/10.1038/s41598-025-98378-1 Floridi, Luciano. “AI as Agency Without Intelligence: on ChatGPT, Large Language Models, and Other Generative Models.” Philosophy and Technology 36, 15 (2023). https://doi.org/10.1007/s13347-023-00621-y Franke, Michael and Gerhard Jäger. “Probabilistic pragmatics, or why Bayes’ rule is probably important for pragmatics.” Zeitschrift für Sprachwissenschaft 35, no. 1 (2016): 3–44. https://doi.org/10.1515/zfs-2016-0002 Gazdar, Gerald. Pragmatics. New York – London: Academic Press, 1979. Grice, Paul. Studies in the Way of Words. Cambridge – London: Harvard University Press, 1989. Goodman, Noah D. and Michael C. Frank. “Pragmatic Language Interpretation as Probabilistic Inference.” Trends in Cognitive Sciences 20, no. 11 (2016): 818–29. https://doi.org/10.1016/j.tics.2016.08.005 Gubelmann, Reto. “Large Language Models, Agency, and Why Speech Acts are Beyond Them (For Now) – A Kantian-Cum-Pragmatist Case.” Philosophy & Technology 37, 32 (2024). https://doi.org/10.1007/s13347-024-00696-1 Gubelmann, Reto. “Pragmatic Norms Are All You Need – Why The Symbol Grounding Problem Does Not Apply to LLMs.” In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 11663–11678. Miami: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.emnlp-main.651 Gunkel, David J. AI for Communication. Boca Raton: CRC Press, 2025. Guo, Zishan et al. “[Evaluating Large Language Models: A Comprehensive Survey](https://md.research.elamur.ai/free/en/papers/guo-2023-evaluating-large-language-models-comprehensive/).” arXiv:2310.19736 [cs.CL], 2023. https://doi.org/10.48550/arXiv.2310.19736 Guzman, Andrea L. ed. Human-Machine Communication. Rethinking Communication, Technology, and Ourselves. New York: Peter Lang, 2018. Guzman, Andrea L. and Seth C. Lewis. “Artificial intelligence and communication: A Human– Machine Communication research agenda.” New Media & Society 22, no. 1 (2019): 70-86. https://doi.org/10.1177/1461444819858691 Harnad, Steven. “The Symbol Grounding Problem.” Physica D 42 (1990): 335–346. Havlík, Vladimír, “Meaning and understanding in large language models.” Synthese 205, no. 9 (2025). https://doi.org/10.1007/s11229-024-04878-4 Hoffmann, Christian R. and Wolfram Bublitz, eds. Pragmatics of Social Media. Berlin – Boston: De Gruyter Mouton, 2017. Jian, Mingyue and N. Siddharth. “Are LLMs good pragmatic speakers?” arXiv:2411.01562 [cs.CL]. 2024. https://doi.org/10.48550/arXiv.2411.01562 Kallini, Julie et al. “Mission: Impossible Language Models.” In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Lun-Wei Ku, Andre Martins and Vivek Srikumar, 14691–14714. Bangkok: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.acl-long.787 Kamath, Gaurav et al. “Scope Ambiguities in Large Language Models.” Transactions of the Association for Computational Linguistics 12 (2024): 738–754. https://doi.org/10.1162/tacl_a_00670 Kaplan, David. “Afterthoughts.” In Themes from Kaplan, edited by Joseph Almog, John Perry and Howard Wettstein. 565–614. New York – Oxford: Oxford University Press, 1989. Keiser, Jessica. Non-Ideal Foundations of Language. New York: Routledge, 2023. Kim, Najoung and Sebastian Schuster. “Entity Tracking in Language Models.” In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Anna Rogers, Jordan Boyd-Graber and Naoaki Okazaki, 3835–3855. Toronto: Association for Computational Linguistics, 2023. https://doi.org/10.18653/v1/2023.acl-long.213 Koyama, Wataru. “The rise of pragmatics: a historiographic overview.” in Foundations of Pragmatics, edited by Wolfram Bublitz and Neal R. Norrick, 139–166. Berlin – Boston: De Gruyter Mouton, 2011. [↗](https://doi.org/10.1007/s11616-022-00754-8) 4. Lipkin, Benjamin et al. “[Evaluating statistical language models as pragmatic reasoners](https://md.research.elamur.ai/free/en/papers/lipkin-2023-evaluating-statistical-language-models-pragmatic/).” arXiv:2305.01020 [cs.CL]. 2023. https://doi.org/10.48550/arXiv.2305.01020 Lee, Ariane. “Are GPT-3 Models Pragmatic Reasoners?” Stanford University. Article accessed March 20, 2025. https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/final-reports/finalreport-169845842.pdf Lewis, David. “Index, Context, and Content.” In Philosophy and Grammar, eds. Stig Kanger and Sven Öhman, 79–100. Dordrecht – Boston – London: D. Reidel, 1980. Mao, Rui et al. “A survey on pragmatic processing techniques.” Information Fusion 114, 102712 (2025). https://doi.org/10.1016/j.inffus.2024.102712 Marwick, Alice E. and danah boyd. “I tweet honestly, I tweet passionately: Twitter users, context collapse, and the imagined audience.” New Media & Society 13, no. (2011): 114–133. https://doi.org/10.1177/1461444810365313 McCoy, R. Thomas et al. “Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve.” arXiv:2309.13638 [cs.CL]. 2023. https://doi.org/10.48550/arXiv.2309.13638 Min, Sewon et al. “AmbigQA: Answering Ambiguous Open-domain Questions.” In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), edited by Bonnie Webber et al., 5783–5797. Online: Association for Computational Linguistics, 2020. https://doi.org/10.18653/v1/2020.emnlp-main.466 Mollo, Dimitri Coelho and Raphaël Millière. “The Vector Grounding Problem.” arXiv:2304.01481 [cs.CL]. 2023. https://doi.org/10.48550/arXiv.2304.01481 Monroe, Will et al. “Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding.” Transactions of the Association for Computational Linguistics 5 (2017): 325–338. https://doi.org/10.1162/tacl_a_00064 Moro, Andrea; Greco, Matteo and Stefano F. Cappa. “Large languages, impossible languages and human brains.” Cortex 167 (2023): 82–85. https://doi.org/10.1016/j.cortex.2023.07.003 Morris, Charles W. Foundations of the Theory of Signs. Chicago: University of Chicago Press, 1938. Nizamani, Rashid, Sebastian Schuster and Vera Demberg. “SIGA: A Naturalistic NLI Dataset of English Scalar Implicatures with Gradable Adjectives.” In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), edited by Nicoletta Calzolari et al., 14784–14795. Torino: ELRA and ICC, 2024. Noveck, Ira A. and Anne Reboul. “Experimental Pragmatics: a Gricean turn in the study of language.” Trends in Cognitive Science 12, no. 11 (2008): 425–431. https://doi.org/10.1016/j.tics.2008.07.009 Noveck, Ira A. and Dan Sperber, eds. Experimental Pragmatics. Basingstoke – New York: Palgrave, 2004. Park, Dojun et al. “MultiPragEval: Multilingual Pragmatic Evaluation of Large Language Models.” In Proceedings of the 2nd GenBench Workshop on Generalisation (Benchmarking) in NLP, edited by Dieuwke Hupkes et al., 96–119. Miami: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.genbench-1.7 Peregrin, Jaroslav. “Do Computers “Have Syntax, But No Semantics”?” Minds and Machines 31, no. 2 (2021): 305–321. https://doi.org/10.1007/s11023-021-09564-9 Piantadosi, Steven T. and Felix Hill. “Meaning without reference in large language models,” arXiv:2208.02957 [cs.CL]. 2022. https://doi.org/10.48550/arXiv.2208.02957 Qiu, Zhuang; Xufeng Duan and Zhenguang Cai. “Does ChatGPT Resemble Humans in Processing Implicatures?” In Proceedings of the 4th Natural Logic Meets Machine Learning Workshop (NALOMA23), edited by Stergios Chatzikyriakidis and Valeria de Paiva, 25–34. Nancy: Association for Computational Linguistics, 2023. Radivojevic, Kristina, Nicholas Clark and Paul Brenner. “LLMs Among Us: Generative AI Participating in Digital Discourse.” arXiv:2402.07940 [cs.HC]. 2024. https://doi.org/10.48550/arXiv.2402.07940 Recanati, Francois. Literal Meaning. New York: Cambridge University Press, 2004. Recanati, Francois. Truth-Conditional Pragmatics. Oxford: Clarendon Press, 2010. [↗](https://doi.org/10.48550/arxiv.2305.01020) 5. Rosen, Zachary P and Rick Dale. “LLMs Don't "Do Things with Words" but Their Lack of Illocution Can Inform the Study of Human Discourse.” Proceedings of the Annual Meeting of the Cognitive Science Society 46 (2024). https://escholarship.org/uc/item/25k7z0mz Ruis, Laura et al. “[The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://md.research.elamur.ai/free/en/papers/ruis-2022-goldilocks-pragmatic-understanding-fine-tuning/).” arXiv:2210.14986 [cs.CL]. 2023. https://doi.org/10.48550/arXiv.2210.14986 Scott, Kate. Pragmatics Online. London – New York: Routledge, 2022. Searle, John. Expression and Meaning. Cambridge: Cambridge University Press, 1979. Searle, John. “Minds, brains, and programs.” Behavioral and Brain Sciences 3, no. 3 (1980): 417– 457. https://doi.org/10.1017/S0140525X00005756 Shisen, Yue et al. “Do Large Language Models Understand Conversational Implicature- A case study with a Chinese sitcom.” In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), edited by Maosong Sun et al., 1270–1285. Taiyuan: Chinese Information Processing Society of China, 2024. Sperber, Dan and Deirdre Wilson. Relevance. Communication and Cognition. Oxford – Cambridge: Blackwell, 1995. Sravanthi, Settaluri et al. “PUB: A Pragmatics Understanding Benchmark for Assessing LLMs’ Pragmatics Capabilities.” In Findings of the Association for Computational Linguistics: ACL 2024, edited by Lun-Wei Ku, Andre Martins and Vivek Srikumar, 12075–12097. Bangkok: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.findings-acl.719 Stalnaker Robert C. Context and Content. Oxford: Oxford University Press, 1999. Sullivan, Emily. “Understanding from Machine Learning Models” The British Journal for the Philosophy of Science 73, no. 1 (2022): 109–133. https://doi.org/10.1093/bjps/axz035 Sundar, S Shyam and Eun-Ju Lee. “Rethinking Communication in the Era of Artificial Intelligence.” Human Communication Research 48, no. 3 (2022): 379–385. https://doi.org/10.1093/hcr/hqac014 Tsvilodub, Polina et al. “Experimental Pragmatics with Machines: Testing LLM Predictions for the Inferences of Plain and Embedded Disjunctions.” arXiv:2405.05776 [cs.CL]. 2024. https://doi.org/10.48550/arXiv.2405.05776 Tsvilodub, Polina et al., “Non-literal Understanding of Number Words by Language Models,” arXiv:2502.06204 [cs.CL]. 2025. https://doi.org/10.48550/arXiv.2502.06204 Turing, Alan. “Computing Machinery and Intelligence.” Mind 59, no. 236 (1950): 433–460. https://doi.org/10.1093/mind/LIX.236.433 White, Jules et al. “A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT.” arXiv:2302.11382 [cs.SE]. 2023. https://doi.org/10.48550/arXiv.2302.11382 Williams, Iwan and Tim Bayne. “Chatting with bots: AI, speech acts, and the edge of assertion,” Inquiry (2024): 1–24. https://doi.org/10.1080/0020174X.2024.2434874 Wu, Shengguang et al. “Rethinking Pragmatics in Large Language Models: Towards Open-Ended Evaluation and Preference Tuning” In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, edited by Yaser Al-Onaizan, Mohit Bansal and Yun-Nung Chen, 22583–22599. Miami: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.emnlp-main.1258 Yakura Hiromu et al. “Empirical evidence of Large Language Model’s influence on human spoken communication.” arXiv:2409.01754v1 [cs.CY]. 2024. https://doi.org/10.48550/arXiv.2409.01754 Yin, Ziqi et al. “Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance,” in Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024), edited by James Hale, Kushal Chawla and Muskan Garg, 9–35. Miami: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.sicon-1.2 Yu, Danni et al. “Assessing the potential of LLM-assisted annotation for corpus-based pragmatics and discourse analysis: The case of apology.” International Journal of Corpus Linguistics 29, no 4 (2024): 534–561. https://doi.org/10.1075/ijcl.23087.yu [↗](https://doi.org/10.48550/arxiv.2210.14986) 6. Zhang, Min et al. “Don’t Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection.” In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Lun-Wei Ku, Andre Martins, Vivek Srikumar, 12073–12086. Bangkok: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.acl-long.652 [↗](https://doi.org/10.18653/v1/2024.acl-long.652) *Updated 29 October 2026*