Elamur Research⌕
☰
home / papers / 2026 / Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives

Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives

Paper · 2026 · Polina Tsvilodub, Fausto Carcassi and Michael Franke

Summary

Pragmatic models need to know which alternatives a speaker or listener weighs: other phrasings the speaker could have used, or other readings the listener might consider. Usually researchers write these sets by hand or collect them from human participants. That keeps models tied to small, closed sets of examples. The authors propose SAGE (ScAffolded Generative models for Explanation), a neuro-symbolic framework with three module types. Proposers use language models to produce open-ended candidates. Evaluators score those candidates, for example on truth, complexity or typicality. Selectors are rule-based and encode an explicit, cognitively motivated task analysis. SAGE is tested in three case studies: referring expression generation, M-implicatures, and Gricean conversational implicatures. The models are judged with standard cognitive-modeling tools: ablations, baseline comparisons and fit to human data. SAGE models reached high accuracy and often beat baselines. A component-level analysis found an asymmetry. LM proposers reliably produced useful alternatives, but LM evaluators handled intuitive judgments much better than formal or theoretical measures. The work points toward pragmatic models that stay transparent yet work on open-ended language.

Key points

  • SAGE has three module types. Proposers (LM-based) generate candidates, evaluators (LM-based) score them, and selectors (symbolic) carry out the steps of the task analysis.
  • Case study 1 covers referring expressions. It builds on an iterative task analysis in the spirit of the Incremental Algorithm (Dale & Reiter, 1995). The LM proposes expressions, an LM evaluator checks their semantics, and success means uniquely identifying the target.
  • Case study 2 covers M-implicatures, analysed with bi-directional optimality. The LM proposes expressions, and evaluators score expression complexity and how likely each world state is.
  • Case study 3 covers Gricean conversational implicatures, analysed as abductive reasoning. The LM proposes interpretations, and evaluators judge whether a maxim is violated and how likely that is.
  • Main finding: LMs are good at proposing simple alternatives and giving intuitive judgments. The authors suggest that what LMs can supply tracks how easily humans can verbalise and introspect on that kind of information.

Interesting ideas

  • I1. Separate open-ended generation from rule-based choice: let a neural model propose candidates, then let explicit, inspectable rules make the final selection. This keeps the decision explainable even when the candidate space is unbounded.
  • I2. Give LMs only the jobs they do well: proposing candidates and making intuitive "does this sound typical/true" calls, not computing formal measures. Formal quantities should be computed symbolically.
  • I3. Build referring expressions incrementally from a freely generated pool of descriptions, checking each against the context to see whether it singles out the target. This turns an open vocabulary into a verifiable, goal-directed procedure.
  • I4. Model M-implicature by scoring both how marked an expression is and how typical the described state is, so that unusual wording signals an unusual situation. Combining these two cheap scores captures a subtle inference.
  • I5. Stress-test each module separately with ablations and baseline swaps, rather than only scoring the end-to-end output. This shows which component actually carries the performance.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (frames): In crate prag, an LLM could propose candidate implicatures or speech-act readings, while the choice among them stays a traceable rule over the frames.
  • I2 (learn): LLM teacher tiers could propose silver candidates and plausibility labels, while measures such as complexity or entailment are computed by Mova's own symbolic code.
  • I3 (back): When generating text from the world graph, candidate descriptions of an entity could be tested against all entities in the world of the text until one is unique.
  • I4 (frames): A marked periphrasis in place of a simple verb could raise the likelihood that the event in the frame was atypical, recorded as an explainable implicature.
  • I5 (learn): Evaluation runs could swap each stage's module for a trivial baseline, as a negative control, to measure what each step contributes.

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

🎓University of AmsterdamAmsterdam · Netherlands144 works · 173,906 citations🎓University of TübingenTübingen · Germany75 works · 41,081 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Polina Tsvilodub, Fausto Carcassi and Michael Franke. 2026. Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives. arXiv:2607.18443.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2607.18443 · arXiv 2607.18443

@misc{tsvilodub2026computational,
  title = {{Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives}},
  author = {Polina Tsvilodub, Fausto Carcassi and Michael Franke},
  year = {2026},
  doi = {10.48550/arxiv.2607.18443},
  eprint = {2607.18443},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2607.18443}
}

References

125 references, 40 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Aher, G. V., Arriaga, R. I., & Kalai, A. T. (2023). Using large language models to simulate multiple humans and replicate human subject studies. International Conference on Machine Learning, 337–371. ↗
  2. Atlas, J. D., & Levinson, S. C. (1981). It-clefts, informativeness and logical form: Radical pragmatics (revised standard version). In Radical pragmatics (pp. 1–62). Academic Press. find
  3. Bavaresco, A., Bernardi, R., Bertolazzi, L., Elliott, D., Fernández, R., Gatt, A., Ghaleb, E., Giulianelli, M., Hanna, M., Koller, A., Martins, A., Mondorf, P., Neplenbroek, V., Pezzelle, S., Plank, B., Schlangen, D., Suglia, A., Surikuchi, A. K., Takmaz, E., & Testoni, A. (2025, July). LLMs instead of human judges? a large scale empirical study across 20 NLP evaluation tasks. In W. Che, J. Nabende, E. Shutova, & M. T. Pilehvar (Eds.), Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 2: Short papers) (pp. 238– 255). Association for Computational Linguistics.
  4. Bender, E. M., Gebru, T., McMillan-Major, A., & Mitchell, M. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–623. find
  5. Benz, A., Jäger, G., & van Rooij, R. (Eds.). (2006). Game theory and pragmatics. Palgrave MacMillan. ↗
  6. Bergen, L., Levy, R., & Goodman, N. D. (2012). That’s what she (could have) said: How alternative utterances affect language use. Proceedings of the 34 th Annual Meeting of the Cognitive Science Society, 34, 120–125. find
  7. Bergen, L., Levy, R., & Goodman, N. D. (2016). Pragmatic reasoning through semantic inference. Semantics & Pragmatics, 9 (20), 1–83. ↗
  8. Bhuyan, B. P., Ramdane-Cherif, A., Tomar, R., & Singh, T. (2024). Neuro-symbolic artificial intelligence: A survey. Neural Computing and Applications, 1–36. ↗
  9. Binz, M., Akata, E., Bethge, M., Brändle, F., Callaway, F., Coda-Forno, J., Dayan, P., Demircan, C., Eckstein, M. K., Éltető, N., et al. (2025). A foundation model to predict and capture human cognition. Nature, 1–8. ↗
  10. Binz, M., Akata, E., Bethge, M., Brändle, F., Callaway, F., Coda-Forno, J., Dayan, P., Demircan, C., Eckstein, M. K., Éltető, N., Griffiths, T. L., Haridi, S., Jagadish, A. K., Ji-An, L., Kipnis, A., Kumar, S., Ludwig, T., Mathony, M., Mattar, M., . . . Schulz, E. (2024). Centaur: A foundation model of human cognition. ↗
  11. Binz, M., & Schulz, E. (2023). Turning large language models into cognitive models. arXiv preprint arXiv:2306.03917. ↗
  12. Blutner, R. (2000). Some aspects of optimality in natural language interpretation. Journal of Semantics, 17, 189–216. ↗
  13. Blutner, R., & Zeevat, H. (Eds.). (2004). Optimality theory and pragmatics. Palgrave MacMillan. find
  14. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258. ↗
  15. Bourgin, D. D., Peterson, J. C., Reichman, D., Russell, S. J., & Griffiths, T. L. (2019). Cognitive model priors for predicting human decisions. International conference on machine learning, 5133–5141. ↗
  16. Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015, September). A large annotated corpus for learning natural language inference. In L. Màrquez, C. Callison-Burch, & J. Su (Eds.), Proceedings of the 2015 conference on empirical methods in natural language processing (pp. 632– 642). Association for Computational Linguistics.
  17. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., . . . Amodei, D. (2020). Language models are few-shot learners. In H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, & H. Lin (Eds.), Advances in neural information processing systems (pp. 1877–1901, Vol. 33). Curran Associates, Inc.
  18. Buccola, B., Križ, M., & Chemla, E. (2021). Conceptual alternatives: Competition in language and beyond. Linguistics and Philosophy, 45 (2), 265–291. find
  19. Bunt, H., & Black, W. (2000). Abduction, belief and context in dialogue. John Benjamins. find
  20. Burgess, C., & Kim, H. (2018). 3d shapes dataset. find
  21. Bürkner, P.-C. (2018). Advanced Bayesian Multilevel Modeling with the R Package brms. The R Journal, 10 (1), 395–411. ↗
  22. Cong, Y. (2024). Manner implicatures in large language models. Scientific Reports, 14 (1), 29113. ↗
  23. Creswell, A., Shanahan, M., & Higgins, I. (2022). Selection-inference: Exploiting large language models for interpretable logical reasoning. arXiv preprint arXiv:2205.09712. ↗
  24. Dale, R., & Reiter, E. (1995). Computational interpretations of the gricean maxims in the generation of referring expressions. Cognitive science, 19 (2), 233–263. ↗
  25. Degen, J. (2023). The rational speech act framework. Annual Review of Linguistics, 9 (1), 519–540. ↗
  26. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019, June). BERT: Pre-training of deep bidirectional transformers for language understanding. In J. Burstein, C. Doran, & T. Solorio (Eds.), Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics: Human language technologies, volume 1 (long and short papers) (pp. 4171–4186). Association for Computational Linguistics.
  27. Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Yang, A., Fan, A., et al. (2024). The llama 3 herd of models. arXiv e-prints, arXiv–2407.
  28. Farrell, S., & Lewandowsky, S. (2018). Computational modeling of cognition and behavior. Cambridge University Press. ↗
  29. Ferreira, V. S. (2019). A mechanistic framework for explaining audience design in language production. Annual Review of Psychology, 70 (1), 29–51. ↗
  30. Fox, D., & Katzir, R. (2011). On the characterization of alternatives. Natural Language Semantics, 19, 87–107. ↗
  31. Frank, M. C. (2023). Large language models as models of human cognition. ↗
  32. Frank, M. C., & Goodman, N. D. (2012). Predicting pragmatic reasoning in language games. Science, 336 (6084), 998–998. ↗
  33. Frank, M. C., & Goodman, N. D. (2025). Cognitive modeling using artificial intelligence. ↗
  34. Franke, M. (2009). Signal to act: Game theory in pragmatics [Doctoral dissertation, Universiteit van Amsterdam]. find
  35. Franke, M. (2011). Quantity implicatures, exhaustive interpretation, and rational conversation. Semantics & Pragmatics, 4 (1), 1–82. ↗
  36. Franke, M., Dablander, F., Bennett, E., Degen, J., Tessler, M. H., Kao, J., Goodman, N. D., et al. (2016). What does the crowd believe? a hierarchical approach to estimating subjective beliefs from empirical data. Proceedings of the Annual Meeting of the Cognitive Science Society, 38. find
  37. Franke, M., Tsvilodub, P., & Carcassi, F. (2024). Bayesian Statistical Modeling with Predictors from LLMs. ↗
  38. Futrell, R., & Mahowald, K. (2025). How linguistics learned to stop worrying and love the language models. arXiv preprint arXiv:2501.17047. ↗
  39. Gandhi, K., Fränken, J.-P., Gerstenberg, T., & Goodman, N. (2023). Understanding social reasoning in language models with language models. Advances in Neural Information Processing Systems, 36, 13518–13529. ↗
  40. Gao, L., Madaan, A., Zhou, S., Alon, U., Liu, P., Yang, Y., Callan, J., & Neubig, G. (2022). Pal: Program-aided language models. arXiv preprint arXiv:2211.10435. ↗
  41. Gatt, A., & Krahmer, E. (2018). Survey of the state of the art in natural language generation: Core tasks, applications and evaluation. Journal of Artificial Intelligence Research, 61, 65–170. ↗
  42. Geurts, B. (2010). Quantity implicatures. Cambridge University Press. find
  43. Gotzner, N., & Romoli, J. (2022). Meaning and alternatives. Annual Review of Linguistics, 8 (1), 213– 234. ↗
  44. Grice, H. P. (1975). Logic and conversation. In Speech acts (pp. 41–58). Brill. ↗
  45. Griffiths, T. L., Zhu, J.-Q., Grant, E., & Thomas McCoy, R. (2024). Bayes in the age of intelligent machines. Current Directions in Psychological Science, 33 (5), 283–291. ↗
  46. Haaf, J. M., & Rouder, J. N. (2019). Some do and some don’t? accounting for variability of individual difference structures. Psychonomic Bulletin & Review, 26, 772–789. ↗
  47. He-Yueya, J., Poesia, G., Wang, R. E., & Goodman, N. D. (2023). Solving math word problems by combining language models with symbolic solvers. arXiv preprint arXiv:2304.09102. ↗
  48. Hobbs, J. R., Stickel, M., & Martin, P. (1993). Interpretation as abduction. Artificial Intelligence, 63, 69–142. find
  49. Holtzman, A., West, P., Shwartz, V., Choi, Y., & Zettlemoyer, L. (2021). Surface form competition: Why the highest probability answer isn’t always right. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 7038–7051.
  50. Horn, L. R. (1984). Towards a new taxonomy for pragmatic inference: Q-based and R-based implicature. In D. Shiffrin (Ed.), Meaning, form, and use in context (pp. 11–42). Georgetown University Press. find
  51. Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al. (2022). Lora: Low-rank adaptation of large language models. ICLR, 1 (2), 3.
  52. Hu, J., Floyd, S., Jouravlev, O., Fedorenko, E., & Gibson, E. (2023). A fine-grained comparison of pragmatic language understanding in humans and language models. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 4194–4213.
  53. Hu, J., & Frank, M. (2024). Auxiliary task demands mask the capabilities of smaller language models. First Conference on Language Modeling. ↗
  54. Hu, J., & Levy, R. (2023, December). Prompting is not a substitute for probability measurements in large language models. In H. Bouamor, J. Pino, & K. Bali (Eds.), Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 5040–5060). Association for Computational Linguistics.
  55. Jäger, G. (2002). Some notes on the formal properties of bidirectional optimality theory. Journal of Logic, Language and Information, 11 (4), 427–451. ↗
  56. Jeretic, P., Warstadt, A., Bhooshan, S., & Williams, A. (2020, July). Are natural language inference models IMPPRESsive? Learning IMPlicature and PRESupposition. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault (Eds.), Proceedings of the 58th annual meeting of the association for computational linguistics (pp. 8690–8705). Association for Computational Linguistics.
  57. Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of hallucination in natural language generation. ACM Comput. Surv., 55 (12). ↗
  58. Kahneman, D., & Tversky, A. (1972). Subjective probability: A judgment of representativeness. Cognitive psychology, 3 (3), 430–454. ↗
  59. Kambhampati, S., Valmeekam, K., Guan, L., Verma, M., Stechly, K., Bhambri, S., Saldyt, L., & Murthy, A. (2024). Llms can’t plan, but can help planning in llm-modulo frameworks. find
  60. Kao, J. T., Bergen, L., & Goodman, N. (2014). Formalizing the pragmatics of metaphor understanding. Proceedings of the annual meeting of the Cognitive Science Society, 36 (36). find
  61. Kao, J. T., Wu, J. Y., Bergen, L., & Goodman, N. D. (2014). Nonliteral understanding of number words. Proceedings of the National Academy of Sciences, 111 (33), 12002–12007. ↗
  62. Katzir, R. (2007). Structurally-defined alternatives. Linguistics and Philosophy, 30 (6), 669–690. ↗
  63. Kidd, E., Donnelly, S., & Christiansen, M. H. (2018). Individual differences in language acquisition and processing. Trends in Cognitive Sciences, 22 (2), 154–169. ↗
  64. Kim, S., Suk, J., Yue, X., Viswanathan, V., Lee, S., Wang, Y., Gashteovski, K., Lawrence, C., Welleck, S., & Neubig, G. (2025, July). Evaluating language models as synthetic data generators. In W. Che, J. Nabende, E. Shutova, & M. T. Pilehvar (Eds.), Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 1: Long papers) (pp. 6385– 6403). Association for Computational Linguistics. ↗
  65. Krahmer, E., & van Deemter, K. (2012). Computational generation of referring expressions: A survey. Computational Linguistics, 38 (1), 173–218. ↗
  66. Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017). Building machines that learn and think like people. Behavioral and brain sciences, 40, e253. ↗
  67. Landau, B., Smith, L. B., & Jones, S. S. (1988). The importance of shape in early lexical learning. Cognitive development, 3 (3), 299–321. ↗
  68. Lassiter, D., & Goodman, N. D. (2017). Adjectival vagueness in a bayesian model of interpretation. Synthese, 194 (10), 3801–3836. find
  69. Levinson, S. C. (2000). Presumptive meanings: The theory of generalized conversational implicature. MIT press. ↗
  70. Lewis, D. (1969). Convention. Cambridge, MA. find
  71. Lipkin, B., LeBrun, B., Vigly, J. H., Loula, J., MacIver, D. R., Du, L., Eisner, J., Cotterell, R., Mansinghka, V., O’Donnell, T. J., Lew, A. K., & Vieira, T. (2025). Fast controlled generation from language models with adaptive weighted rejection sampling. Second Conference on Language Modeling. ↗
  72. Liu, A., Swayamdipta, S., Smith, N. A., & Choi, Y. (2022, December). WANLI: Worker and AI collaboration for natural language inference dataset creation. In Y. Goldberg, Z. Kozareva, & Y. Zhang (Eds.), Findings of the association for computational linguistics: Emnlp 2022 (pp. 6826–6847). Association for Computational Linguistics.
  73. Liu, H., Ning, R., Teng, Z., Liu, J., Zhou, Q., & Zhang, Y. (2023). Evaluating the logical reasoning ability of chatgpt and gpt-4. arXiv preprint arXiv:2304.03439. ↗
  74. Liu, J., Liu, A., Lu, X., Welleck, S., West, P., Le Bras, R., Choi, Y., & Hajishirzi, H. (2022). Generated knowledge prompting for commonsense reasoning. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 3154–3169. ↗
  75. Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2023). Lost in the middle: How language models use long contexts. ↗
  76. Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., Yang, K., et al. (2023). Agentbench: Evaluating LLMs as agents. arXiv preprint arXiv:2308.03688. ↗
  77. Marr, D. (2010). Vision: A computational investigation into the human representation and processing of visual information. MIT press. find
  78. McCoy, R. T., Yao, S., Friedman, D., Hardy, M., & Griffiths, T. L. (2023). Embers of autoregression: Understanding large language models through the problem they are trained to solve. arXiv preprint arXiv:2309.13638. ↗
  79. Moskal, M., Musuvathi, M., & Kıcıman, E. (2024). AI Controller Interface. find
  80. Newell, A., Simon, H. A., et al. (1972). Human problem solving (Vol. 104). Prentice-hall Englewood Cliffs, NJ. find
  81. Nye, M., Tessler, M., Tenenbaum, J., & Lake, B. M. (2021). Improving coherence and consistency in neural sequence models with dual-system, neuro-symbolic reasoning. Advances in Neural Information Processing Systems, 34, 25192–25204. ↗
  82. OpenAI. (2023). Gpt-4 technical report.
  83. 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.
  84. Paranjape, B., Lundberg, S., Singh, S., Hajishirzi, H., Zettlemoyer, L., & Ribeiro, M. T. (2023). ART: Automatic multi-step reasoning and tool-use for large language models. arXiv preprint arXiv:2303.09014. ↗
  85. Parikh, P. (1988). Language and strategic inference [Doctoral dissertation, Stanford University]. find
  86. Parikh, P. (1992). A game-theoretic account of implicature. In Y. Moses (Ed.), Tark ’92: Proceedings of the 4th conference on theoretical aspects of reasoning about knowledge (pp. 85–94). Morgan Kaufmann Publishers Inc. find
  87. Park, J. S., O’Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023). Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, 1–22. find
  88. Perez, E., Ringer, S., Lukošiūtė, K., Nguyen, K., Chen, E., Heiner, S., Pettit, C., Olsson, C., Kundu, S., Kadavath, S., et al. (2022). Discovering language model behaviors with model-written evaluations. arXiv preprint arXiv:2212.09251. ↗
  89. Petroni, F., Rocktäschel, T., Lewis, P., Bakhtin, A., Wu, Y., Miller, A. H., & Riedel, S. (2019). Language models as knowledge bases? arXiv preprint arXiv:1909.01066. ↗
  90. Poesia, G., Gandhi, K., Zelikman, E., & Goodman, N. D. (2023). Certified deductive reasoning with language models. ↗
  91. Poliak, A., Naradowsky, J., Haldar, A., Rudinger, R., & Van Durme, B. (2018). Hypothesis only baselines in natural language inference. Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, 180–191.
  92. Repp, S., & Spalek, K. (2021). The role of alternatives in language. Frontiers in Communication, 6. ↗
  93. Rett, J. (2020). Manner implicatures and how to spot them. International Review of Pragmatics, 12 (1), 44–79. ↗
  94. Romero, O. J., Zimmerman, J., Steinfeld, A., & Tomasic, A. (2023). Synergistic integration of large language models and cognitive architectures for robust ai: An exploratory analysis. Proceedings of the AAAI Symposium Series, 2 (1), 396–405. find
  95. Rutar, D., Wolff, E. d., Rooij, I. v., & Kwisthout, J. (2022). Structure Learning in Predictive Processing Needs Revision. Computational Brain & Behavior, 1–10. ↗
  96. Salewski, L., Alaniz, S., Rio-Torto, I., Schulz, E., & Akata, Z. (2023). In-context impersonation reveals large language models’ strengths and biases. Advances in neural information processing systems, 36, 72044–72057. find
  97. Schaeffer, R., Pistunova, K., Khanna, S., Consul, S., & Koyejo, S. (2023). Invalid logic, equivalent gains: The bizarreness of reasoning in language model prompting. ↗
  98. Shanahan, M. (2024). Simulacra as conscious exotica. Inquiry, 1–29. ↗
  99. Shi, F., Chen, X., Misra, K., Scales, N., Dohan, D., Chi, E., Schärli, N., & Zhou, D. (2023). Large language models can be easily distracted by irrelevant context. ↗
  100. Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., & Yao, S. (2023). Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36, 8634–8652.
  101. van Deemter, K. (2023). Dimensions of explanatory value in nlp models. Computational Linguistics. ↗
  102. van Rooij, R., & Franke, M. (2015). Optimality-theoretic and game-theoretic approaches to implicatures [Winter 2015 Edition]. In The stanford encyclopedia of philosophy. Stanford University. find
  103. Sperber, D., & Wilson, D. (1995). Relevance: Communication and cognition (2nd ed.) Blackwell. find
  104. Spinoso-Di Piano, C. (2025). (rsa)ˆ 2: A rhetorical-strategy-aware rational speech act framework for figurative language understanding. Society for Computation in Linguistics, 8 (1). find
  105. Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022). Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615. ↗
  106. Stanovich, K. E., & West, R. F. (2000). Individual differences in reasoning: Implications for the rationality debate? Behavioral and Brain Sciences, 23 (5), 645–665. ↗
  107. Sucholutsky, I., Collins, K. M., Jacoby, N., Thompson, B. D., & Hawkins, R. D. (2025). Using llms to advance the cognitive science of collectives. arXiv preprint arXiv:2506.00052. ↗
  108. Sumers, T., Yao, S., Narasimhan, K., & Griffiths, T. L. (2023). Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427. ↗
  109. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971. ↗
  110. Tsvilodub, P., & Franke, M. (2023). Evaluating pragmatic abilities of image captioners on a3ds. ↗
  111. Tsvilodub, P., Franke, M., & Carcassi, F. (2024). Cognitive modeling with scaffolded llms: A case study of referential expression generation. arXiv preprint arXiv:2407.03805. ↗
  112. Tsvilodub, P., Gandhi, K., Zhao, H., Fränken, J.-P., Franke, M., & Goodman, N. D. (2025). Non-literal understanding of number words by language models. arXiv preprint arXiv:2502.06204. ↗
  113. Tsvilodub, P., Hawkins, R. D., & Franke, M. (2025). Integrating neural and symbolic components in a model of pragmatic question-answering. Society for Computation in Linguistics, 8 (1). ↗
  114. Van Rooij, I., Guest, O., Adolfi, F., de Haan, R., Kolokolova, A., & Rich, P. (2024). Reclaiming ai as a theoretical tool for cognitive science. Computational Brain & Behavior, 7 (4), 616–636. ↗
  115. Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2019). Superglue: A stickier benchmark for general-purpose language understanding systems. Advances in neural information processing systems, 32.
  116. Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18 (6), 186345. ↗
  117. Wang, X., Wei, J., Schuurmans, D., Le, Q. V., Chi, E. H., Narang, S., Chowdhery, A., & Zhou, D. (2023). Self-consistency improves chain of thought reasoning in language models. The Eleventh International Conference on Learning Representations. ↗
  118. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Chi, E., Le, Q., & Zhou, D. (2022). Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903. ↗
  119. Wieling, M., Rawee, J., & van Noord, G. (2018). Reproducibility in computational linguistics: Are we willing to share? Computational Linguistics, 44 (4), 641–649. ↗
  120. Wilson, E., & Katsos, N. (2016). In a manner of speaking: An empirical investigation of manner implicatures. Pre-proceedings of Trends in Experimental Pragmatics, 170–176. find
  121. Wong, L., Collins, K. M., Ying, L., Zhang, C. E., Weller, A., Gersternberg, T., O’Donnell, T., Lew, A. K., Andreas, J. D., Tenenbaum, J. B., et al. (2025). Modeling open-world cognition as on-demand synthesis of probabilistic models. arXiv preprint arXiv:2507.12547. ↗
  122. Wong, L., Grand, G., Lew, A. K., Goodman, N. D., Mansinghka, V. K., Andreas, J., & Tenenbaum, J. B. (2023). From word models to world models: Translating from natural language to the probabilistic language of thought. ↗
  123. Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023). Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601. ↗
  124. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). React: Synergizing reasoning and acting in language models. International Conference on Learning Representations (ICLR).
  125. Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2023). Explainability for large language models: A survey. ACM Transactions on Intelligent Systems and Technology. Algorithm 1 Iterative model for contrastive utterance generation 1: procedure Generate(s ∗ , D, n) 2: partialUtt ← [] ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tsvilodub-2026-computational-models-pragmatic-reasoning-flexible/