arXiv cs.CL· Maxime Toquebiau, J\'er\^ome Botoko Ekila, Paul Van Eecke, Katrien Beuls·· 11 小时前AI 评分31
文化演化驱动神经涌现通信中惯例的形成
Cultural Evolution Drives the Emergence of Conventions in Neural Emergent Communication
AI 导读
研究提出一种新模型，以完全分布式方式训练双向神经智能体群体解决指称游戏，从而研究语言如何通过文化演化涌现。该模型在多个图像数据集上验证有效，可扩展至大规模群体，并发现越常规的语言越易学习，为文化传递带来直接优势。
正文 · 原文
Abstract:Recent studies of language evolution with neural agents often use models where agents can either speak or listen, where there are only two agents in the population, or where agents can share internal representations. These choices prevent the study of how language emerges through cultural evolution, i.e. through the cumulative adaptation of individual behaviours to fit the communicative needs of the community. We tackle this issue with a new model that trains populations of bi-directional neural agents in a fully distributed fashion to solve a referential game. We demonstrate the effectiveness of this approach on multiple image datasets and show that it is able to scale to large populations. We also show that more conventional languages are easier to learn, providing a direct advantage for cultural transmission. Overall, this work provides a novel approach to neural emergent communication that opens up new directions for evolutionary linguistics.
| Subjects: | Neural and Evolutionary Computing (cs.NE); Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.00006 [cs.NE] |
| (or arXiv:2611.00006v2 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.00006 arXiv-issued DOI via DataCite |
|
| Journal reference: | Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, p32202-32223 |
| Related DOI: | https://doi.org/10.18653/2026.emnlp-main.1410
DOI(s) linking to related resources |
Submission history
From: Maxime Toquebiau PhD [view email]
[v1]
Mon, 24 Aug 2026 15:26:33 UTC (905 KB)
[v2]
Tue, 3 Nov 2026 10:10:27 UTC (913 KB)
来源：arXiv cs.CL · arxiv.org