# A Rate-Distortion view of human pragmatic reasoning

arXiv: https://arxiv.org/abs/2005.06641 · HTML: https://mlsanity.com/paper/2005.06641/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2020.

## Built on by (most cited first, 19 of 19)

- [From partners to populations: A hierarchical Bayesian account of coordination and convention](https://mlsanity.com/paper/2104.05857/) (2021)
- [Semantics-Native Communication with Contextual Reasoning](https://mlsanity.com/paper/2108.05681/) (2021)
- [Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches](https://mlsanity.com/paper/2211.08371/) (2022)
- [Towards Pragmatic Production Strategies for Natural Language Generation Tasks](https://mlsanity.com/paper/2210.12828/) (2022)
- [Concept-Best-Matching: Evaluating Compositionality in Emergent Communication](https://mlsanity.com/paper/2403.14705/) (2024)
- [A practical introduction to the Rational Speech Act modeling framework](https://mlsanity.com/paper/2105.09867/) (2021)
- [An information-theoretic model of shallow and deep language comprehension](https://mlsanity.com/paper/2405.08223/) (2024)
- [GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews](https://mlsanity.com/paper/2406.07359/) (2024)
- [Bayesian Reinforcement Learning with Limited Cognitive Load](https://mlsanity.com/paper/2305.03263/) (2023)
- [Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning](https://mlsanity.com/paper/2311.09712/) (2023)
- [Bayesian Inverse Contextual Reasoning for Heterogeneous Semantics-Native Communication](https://mlsanity.com/paper/2306.06403/) (2023)
- [Why do objects have many names? A study on word informativeness in language use and lexical systems](https://mlsanity.com/paper/2410.07827/) (2024)
- [Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog](https://mlsanity.com/paper/2507.14063/) (2025)
- [Scalable pragmatic communication via self-supervision](https://mlsanity.com/paper/2108.05799/) (2021)
- [The Alignment Bottleneck](https://mlsanity.com/paper/2509.15932/) (2025)
- [CtD: Composition through Decomposition in Emergent Communication](https://mlsanity.com/paper/2601.10169/) (2026)
- [Systematicity between Forms and Meanings across Languages Supports Efficient Communication](https://mlsanity.com/paper/2601.17181/) (2026)
- [Exhaustivity and anti-exhaustivity in the RSA framework: Testing the effect of prior beliefs](https://mlsanity.com/paper/2202.07023/) (2022)
- [Pragmatic Reasoning in Structured Signaling Games](https://mlsanity.com/paper/2305.10167/) (2023)

## Abstract (arXiv)

What computational principles underlie human pragmatic reasoning? A prominent approach to pragmatics is the Rational Speech Act (RSA) framework, which formulates pragmatic reasoning as probabilistic speakers and listeners recursively reasoning about each other. While RSA enjoys broad empirical support, it is not yet clear whether the dynamics of such recursive reasoning may be governed by a general optimization principle. Here, we present a novel analysis of the RSA framework that addresses this question. First, we show that RSA recursion implements an alternating maximization for optimizing a tradeoff between expected utility and communicative effort. On that basis, we study the dynamics of RSA recursion and disconfirm the conjecture that expected utility is guaranteed to improve with recursion depth. Second, we show that RSA can be grounded in Rate-Distortion theory, while maintaining a similar ability to account for human behavior and avoiding a bias of RSA toward random utterance production. This work furthers the mathematical understanding of RSA models, and suggests that general information-theoretic principles may give rise to human pragmatic reasoning.