mlsanityData to 7 Oct 2026

Searching for Structure: Investigating Emergent Communication with Large Language Models

arXiv 2412.07646 ↗First posted 10 Dec 2024cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper, we investigate whether the same happens if artificial languages are optimised for implicit biases of Large Language Models (LLMs). To this end, we simulate a classical referential game in which LLMs learn and use artificial languages. Our results show that initially unstructured holistic languages are indeed shaped to have some structural properties that allow two LLM agents to communicate successfully. Similar to observations in human experiments, generational transmission increases the learnability of languages, but can at the same time result in non-humanlike degenerate vocabularies. Taken together, this work extends experimental findings, shows that LLMs can be used as tools in simulations of language evolution, and opens possibilities for future human-machine experiments in this field.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 20 of its 66 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

20 of 66 references.

References · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  7. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  8. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 168
  9. 2023Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMscited by 121
  10. 2024A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'cited by 114
  11. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  12. 2024Auxiliary task demands mask the capabilities of smaller language modelscited by 54
8 more
  1. 2023Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learningcited by 31
  2. 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
  3. 2024A Study on Large Language Models' Limitations in Multiple-Choice Question Answeringcited by 22
  4. 2023Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understandingcited by 20
  5. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  6. 2024Learning and communication pressures in neural networks: Lessons from emergent communicationcited by 8
  7. 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
  8. 2024The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communicationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 2025Agentic Large Language Models, a surveycited by 105
  2. 2025Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interactioncited by 9
  3. 2026From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agentscited by 4
  4. 2025Evolution and compression in LLMs: On the emergence of human-aligned categorizationcited by 1
  5. 2026GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactionscited by 1
  6. 2026When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoningcited by 0
  7. 2026Lexical discovery in unknown environments orchestrated by Large Language Modelscited by 0
  8. 2026ConlangBench: Exploring Language Knowledge and Learning in LLMs through Diverse Constructed Languagescited by 0
  9. 2026Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulationscited by 0
  10. 2026Communication between Frozen Large Language Models via Prompt Optimization in a Referential Gamecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
  2. 2024From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition
  3. 2025From Grunts to Lexicons: Emergent Language from Cooperative Foraging
  4. 2024When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings
  5. 2025EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
  6. 2024Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions
  7. 2026Human-AI Co-Evolution and Epistemic Collapse: A Dynamical Systems Perspective
  8. 2024Generative Emergent Communication: Large Language Model is a Collective World Model