Searching for the Most Human-like Emergent Language

Brendon Boldt, David Mortensen
10/3/2025
cs.CL

No confident code implementation found for this paper.

Abstract

In this paper, we design a signalling game-based emergent communication environment to generate state-of-the-art emergent languages in terms of similarity to human language. This is done with hyperparameter optimization, using XferBench as the objective function. XferBench quantifies the statistical similarity of emergent language to human language by measuring its suitability for deep transfer learning to human language. Additionally, we demonstrate the predictive power of entropy on the transfer learning performance of emergent language as well as corroborate previous results on the entropy-minimization properties of emergent communication systems. Finally, we report generalizations regarding what hyperparameters produce more realistic emergent languages, that is, ones which transfer better to human language.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Searching for Structure: Investigating Emergent Communication with Large Language Models

85% match2024

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

83% match2025

XferBench: a Data-Driven Benchmark for Emergent Language

82% match2024

A Review of the Applications of Deep Learning-Based Emergent Communication

82% match2024

Emergent Language: A Survey and Taxonomy

82% match2024

Agent-based imitation dynamics can yield efficiently compressed population-level vocabularies

82% match2026

Cite this paper

@article{boldt2025searching,
  title  = {Searching for the Most Human-like Emergent Language},
  author = {Brendon Boldt and David Mortensen},
  year   = {2025},
  eprint = {2510.03467},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.03467v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.03467.svg)](https://codeofpaper.com/paper/2510.03467)

Discussion