# Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication

arXiv: https://arxiv.org/abs/2503.04395 · HTML: https://mlsanity.com/paper/2503.04395/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 64 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs](https://mlsanity.com/paper/2309.07311/) (2023)
- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Verbosity Bias in Preference Labeling by Large Language Models](https://mlsanity.com/paper/2310.10076/) (2023)
- ["My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models](https://mlsanity.com/paper/2402.14499/) (2024)
- [Machine Culture](https://mlsanity.com/paper/2311.11388/) (2023)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Mission: Impossible Language Models](https://mlsanity.com/paper/2401.06416/) (2024)
- [Language Models as Models of Language](https://mlsanity.com/paper/2408.07144/) (2024)
- [A distributional simplicity bias in the learning dynamics of transformers](https://mlsanity.com/paper/2410.19637/) (2024)
- [Bayes in the age of intelligent machines](https://mlsanity.com/paper/2311.10206/) (2023)
- [A Study on Large Language Models' Limitations in Multiple-Choice Question Answering](https://mlsanity.com/paper/2401.07955/) (2024)
- [Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding](https://mlsanity.com/paper/2310.19671/) (2023)
- [Bias Amplification in Language Model Evolution: An Iterated Learning Perspective](https://mlsanity.com/paper/2404.04286/) (2024)
- [A Roadmap towards Machine Intelligence](https://mlsanity.com/paper/1511.08130/) (2015)
- [What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure](https://mlsanity.com/paper/2302.12239/) (2023)
- [Learning and communication pressures in neural networks: Lessons from emergent communication](https://mlsanity.com/paper/2403.14427/) (2024)
- [The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication](https://mlsanity.com/paper/2407.17960/) (2024)
- [What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language models](https://mlsanity.com/paper/2407.17974/) (2024)

## Built on by (most cited first, 10 of 10)

- [ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline](https://mlsanity.com/paper/2508.06094/) (2025)
- [Investigating the Development of Task-Oriented Communication in Vision-Language Models](https://mlsanity.com/paper/2601.20641/) (2026)
- [Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs](https://mlsanity.com/paper/2507.03933/) (2025)
- [Model Collapse as Cultural Evolution](https://mlsanity.com/paper/2605.23054/) (2026)
- [Private Etymology: Designing Relational Reuse of Shared Symbols in Long-Term Human-AI Interaction](https://mlsanity.com/paper/2608.08443/) (2026)
- [Traces of Social Competence in Large Language Models](https://mlsanity.com/paper/2603.04161/) (2026)
- [Translating Signals to Languages for sEMG-Based Activity Recognition](https://mlsanity.com/paper/2605.22403/) (2026)
- [A Dynamic-Semantics Framework for Grounding Human Referring Expressions in Visual Perceptual Data](https://mlsanity.com/paper/2608.08663/) (2026)
- [Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features](https://mlsanity.com/paper/2608.28986/) (2026)
- [KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?](https://mlsanity.com/paper/2610.19399/) (2026)

## Abstract (arXiv)

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human, LLM-LLM and Human-LLM experiments. We show that referentially grounded vocabularies emerge that enable reliable communication in all conditions, even when humans textitand LLMs collaborate. Comparisons between conditions reveal that languages optimised for LLMs subtly differ from those optimised for humans. Interestingly, interactions between humans and LLMs alleviate these differences and result in vocabularies more human-like than LLM-like. These findings advance our understanding of the role inductive biases in LLMs play in the dynamic nature of human language and contribute to maintaining alignment in human and machine communication. In particular, our work underscores the need to think of new LLM training methods that include human interaction and shows that using communicative success as a reward signal can be a fruitful, novel direction.