# Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning

arXiv: https://arxiv.org/abs/2311.09712 · HTML: https://mlsanity.com/paper/2311.09712/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding](https://mlsanity.com/paper/1703.10186/) (2017)
- [Modeling Strong and Human-Like Gameplay with KL-Regularized Search](https://mlsanity.com/paper/2112.07544/) (2021)
- [Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning](https://mlsanity.com/paper/2210.05492/) (2022)
- [The Consensus Game: Language Model Generation via Equilibrium Search](https://mlsanity.com/paper/2310.09139/) (2023)
- [Continual adaptation for efficient machine communication](https://mlsanity.com/paper/1911.09896/) (2019)
- [From partners to populations: A hierarchical Bayesian account of coordination and convention](https://mlsanity.com/paper/2104.05857/) (2021)
- [A Rate-Distortion view of human pragmatic reasoning](https://mlsanity.com/paper/2005.06641/) (2020)

## Built on by (most cited first, 4 of 4)

- [Nash Learning from Human Feedback](https://mlsanity.com/paper/2312.00886/) (2023)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [Conversation Games and a Strategic View of the Turing Test](https://mlsanity.com/paper/2501.18455/) (2025)
- [Provably Optimal Learning Algorithms for Assistance Games](https://mlsanity.com/paper/2607.08012/) (2026)

## Abstract (arXiv)

We present a model of pragmatic language understanding, where utterances are produced and understood by searching for regularized equilibria of signaling games. In this model (which we call ReCo, for Regularized Conventions), speakers and listeners search for contextually appropriate utterance--meaning mappings that are both close to game-theoretically optimal conventions and close to a shared, ''default'' semantics. By characterizing pragmatic communication as equilibrium search, we obtain principled sampling algorithms and formal guarantees about the trade-off between communicative success and naturalness. Across several datasets capturing real and idealized human judgments about pragmatic implicatures, ReCo matches or improves upon predictions made by best response and rational speech act models of language understanding.