# From partners to populations: A hierarchical Bayesian account of coordination and convention

arXiv: https://arxiv.org/abs/2104.05857 · HTML: https://mlsanity.com/paper/2104.05857/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 272 references that are in the map.
- First posted on arXiv 12 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks](https://mlsanity.com/paper/1502.05336/) (2015)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Recasting Gradient-Based Meta-Learning as Hierarchical Bayes](https://mlsanity.com/paper/1801.08930/) (2018)
- [Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors](https://mlsanity.com/paper/2005.07186/) (2020)
- [Subspace Inference for Bayesian Deep Learning](https://mlsanity.com/paper/1907.07504/) (2019)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding](https://mlsanity.com/paper/1703.10186/) (2017)
- [ShapeGlot: Learning Language for Shape Differentiation](https://mlsanity.com/paper/1905.02925/) (2019)
- [Pragmatically Informative Image Captioning with Character-Level Inference](https://mlsanity.com/paper/1804.05417/) (2018)
- [Emergent Linguistic Phenomena in Multi-Agent Communication Games](https://mlsanity.com/paper/1901.08706/) (2019)
- [Characterizing the dynamics of learning in repeated reference games](https://mlsanity.com/paper/1912.07199/) (2019)
- [Pragmatically Informative Text Generation](https://mlsanity.com/paper/1904.01301/) (2019)
- [Continual adaptation for efficient machine communication](https://mlsanity.com/paper/1911.09896/) (2019)
- [Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts](https://mlsanity.com/paper/2011.04554/) (2020)
- [When redundancy is useful: A Bayesian approach to 'overinformative' referring expressions](https://mlsanity.com/paper/1903.08237/) (2019)
- [A Rate-Distortion view of human pragmatic reasoning](https://mlsanity.com/paper/2005.06641/) (2020)
- [A Neural Model of Adaptation in Reading](https://mlsanity.com/paper/1808.09930/) (2018)
- [The Spontaneous Emergence of Conventions: An Experimental Study of Cultural Evolution](https://mlsanity.com/paper/1502.06910/) (2015)
- [Pragmatic inference and visual abstraction enable contextual flexibility during visual communication](https://mlsanity.com/paper/1903.04448/) (2019)
- [Shaping representations through communication: community size effect in artificial learning systems](https://mlsanity.com/paper/1912.06208/) (2019)
- [An Incremental Iterated Response Model of Pragmatics](https://mlsanity.com/paper/1810.00367/) (2018)
- [Low-Rank RNN Adaptation for Context-Aware Language Modeling](https://mlsanity.com/paper/1710.02603/) (2017)
- [Uncertainty in Multitask Transfer Learning](https://mlsanity.com/paper/1806.07528/) (2018)
- [Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks](https://mlsanity.com/paper/2002.01510/) (2020)
- [A case for deep learning in semantics](https://mlsanity.com/paper/1809.03068/) (2018)
- [Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks](https://mlsanity.com/paper/2004.03902/) (2020)

## Built on by (most cited first, 27 of 27)

- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [How to talk so AI will learn: Instructions, descriptions, and autonomy](https://mlsanity.com/paper/2206.07870/) (2022)
- [Learning to Mediate Disparities Towards Pragmatic Communication](https://mlsanity.com/paper/2203.13685/) (2022)
- [Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches](https://mlsanity.com/paper/2211.08371/) (2022)
- [Concept Alignment](https://mlsanity.com/paper/2401.08672/) (2024)
- [Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People](https://mlsanity.com/paper/2510.20886/) (2025)
- [From "um" to "yeah": Producing, predicting, and regulating information flow in human conversation](https://mlsanity.com/paper/2403.08890/) (2024)
- [CoGen: Learning from Feedback with Coupled Comprehension and Generation](https://mlsanity.com/paper/2408.15992/) (2024)
- [Success and Cost Elicit Convention Formation for Efficient Communication](https://mlsanity.com/paper/2510.24023/) (2025)
- [Using LLMs to Advance the Cognitive Science of Collectives](https://mlsanity.com/paper/2506.00052/) (2025)
- [Shades of confusion: Lexical uncertainty modulates ad hoc coordination in an interactive communication task](https://mlsanity.com/paper/2105.06546/) (2021)
- [Linguistic Structure from a Bottleneck on Sequential Information Processing](https://mlsanity.com/paper/2405.12109/) (2024)
- [Norm Participation Grounds Language](https://mlsanity.com/paper/2206.02885/) (2022)
- [Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning](https://mlsanity.com/paper/2311.09712/) (2023)
- [A hierarchical Bayesian model for syntactic priming](https://mlsanity.com/paper/2405.15964/) (2024)
- [Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks](https://mlsanity.com/paper/2602.08914/) (2026)
- [Know your audience: specializing grounded language models with listener subtraction](https://mlsanity.com/paper/2206.08349/) (2022)
- [Cognitive Spillover in Human-AI Teams](https://mlsanity.com/paper/2407.17489/) (2024)
- [Mixed-effects transformers for hierarchical adaptation](https://mlsanity.com/paper/2205.01749/) (2022)
- [Semantic uncertainty guides the extension of conventions to new referents](https://mlsanity.com/paper/2305.06539/) (2023)
- [Communicating with Speakers and Listeners of Different Pragmatic Levels](https://mlsanity.com/paper/2410.05851/) (2024)
- [Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation](https://mlsanity.com/paper/2605.01750/) (2026)
- [Ad hoc conventions generalize to new referents](https://mlsanity.com/paper/2509.05566/) (2025)
- [Context informs pragmatic interpretation in vision-language models](https://mlsanity.com/paper/2511.03908/) (2025)
- [Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions](https://mlsanity.com/paper/2606.08081/) (2026)
- [Language Has Two Parameters: Narrative-Induced Semantic Plasticity and Phase-Sensitive Interpretation](https://mlsanity.com/paper/2608.18041/) (2026)
- [Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretation](https://mlsanity.com/paper/2608.29571/) (2026)

## Abstract (arXiv)

Languages are powerful solutions to coordination problems: they provide stable, shared expectations about how the words we say correspond to the beliefs and intentions in our heads. Yet language use in a variable and non-stationary social environment requires linguistic representations to be flexible: old words acquire new ad hoc or partner-specific meanings on the fly. In this paper, we introduce CHAI (Continual Hierarchical Adaptation through Inference), a hierarchical Bayesian theory of coordination and convention formation that aims to reconcile the long-standing tension between these two basic observations. We argue that the central computational problem of communication is not simply transmission, as in classical formulations, but continual learning and adaptation over multiple timescales. Partner-specific common ground quickly emerges from social inferences within dyadic interactions, while community-wide social conventions are stable priors that have been abstracted away from interactions with multiple partners. We present new empirical data alongside simulations showing how our model provides a computational foundation for several phenomena that have posed a challenge for previous accounts: (1) the convergence to more efficient referring expressions across repeated interaction with the same partner, (2) the gradual transfer of partner-specific common ground to strangers, and (3) the influence of communicative context on which conventions eventually form.