mlsanityData to 14 Oct 2026

Emergent Communication for Understanding Human Language Evolution: What's Missing?

arXiv 2204.10590 ↗First posted 22 Apr 2022cs.CL cs.LG cs.NEcited by 23

Not on the map. Why?

Abstract (arXiv)

Emergent communication protocols among humans and artificial neural network agents do not yet share the same properties and show some critical mismatches in results. We describe three important phenomena with respect to the emergence and benefits of compositionality: ease-of-learning, generalization, and group size effects (i.e., larger groups create more systematic languages). The latter two are not fully replicated with neural agents, which hinders the use of neural emergent communication for language evolution research. We argue that one possible reason for these mismatches is that key cognitive and communicative constraints of humans are not yet integrated. Specifically, in humans, memory constraints and the alternation between the roles of speaker and listener underlie the emergence of linguistic structure, yet these constraints are typically absent in neural simulations. We suggest that introducing such communicative and cognitive constraints would promote more linguistically plausible behaviors with neural agents.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 16 of its 52 references that are in the map. First posted on arXiv 22 Apr 2022.

Builds on

16 of 52 references.

References · 16

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  3. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 672
  4. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 185
  5. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 170
  6. 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 125
  7. 2020Compositionality and Generalization in Emergent Languagescited by 103
  8. 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
  9. 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
  10. 2019Ease-of-Teaching and Language Structure from Emergent Communicationcited by 65
  11. 2019Anti-efficient encoding in emergent communicationcited by 59
  12. 2019Emergent Linguistic Phenomena in Multi-Agent Communication Gamescited by 36
4 more
  1. 2019Capacity, Bandwidth, and Compositionality in Emergent Language Learningcited by 30
  2. 2019The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agentscited by 26
  3. 2020"LazImpa": Lazy and Impatient neural agents learn to communicate efficientlycited by 23
  4. 2019Shaping representations through communication: community size effect in artificial learning systemscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 8; 2025: 5; 2026: 2.

23 papers.

Sort:

By area:

  1. 2022Context Limitations Make Neural Language Models More Human-Likecited by 34
  2. 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
  3. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  4. 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
  5. 2023What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structurecited by 13
  6. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  7. 2023Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segmentscited by 11
  8. 2024Emergent Word Order Universals from Cognitively-Motivated Language Modelscited by 11
  9. 2024Searching for Structure: Investigating Emergent Communication with Large Language Modelscited by 10
  10. 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
  11. 2024The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communicationcited by 7
  12. 2024Language Evolution with Deep Learningcited by 5
11 more
  1. 2025Simulating the Emergence of Differential Case Marking with Communicating Neural-Network Agentscited by 5
  2. 2025EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulationcited by 5
  3. 2024What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language modelscited by 3
  4. 2023A framework for the emergence and analysis of language in social learning agentscited by 2
  5. 2026Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasioncited by 2
  6. 2023On the Correspondence between Compositionality and Imitation in Emergent Neural Communicationcited by 1
  7. 2024XferBench: a Data-Driven Benchmark for Emergent Languagecited by 1
  8. 2025From Grunts to Lexicons: Emergent Language from Cooperative Foragingcited by 1
  9. 2025Discovering Properties of Inflectional Morphology in Neural Emergent Communicationcited by 0
  10. 2025Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGIcited by 0
  11. 2026Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulationscited by 0