This paper develops a natural-language agent-based model of argumentation (ABMA). Its artificial deliberative agents (ADAs) are constructed with the help of so-called neural language models recently developed in AI and computational linguistics. ADAs are equipped with a minimalist belief system and may generate and submit novel contributions to a conversation. The natural-language ABMA allows us to simulate collective deliberation in English, i.e. with arguments, reasons, and claims themselves—rather than with their mathematical representations (as in formal models). This paper uses the natural-language ABMA to test the robustness of formal reason-balancing models of argumentation [Mäs and Flache, 2013, Singer et al., 2019]: First of all, as long as ADAs remain passive, confirmation bias and homophily updating trigger polarization, which is consistent with results from formal models. However, once ADAs start to actively generate new contributions, the evolution of a conservation is dominated by properties of the agents as authors. This suggests that the creation of new arguments, reasons, and claims critically affects a conversation and is of pivotal importance for understanding the dynamics of collective deliberation. The paper closes by pointing out further fruitful applications of the model and challenges for future research.

中文翻译：

---

争论性意见动态的自然语言多智能体模拟

本文开发了一种基于自然语言代理的论证模型（ABMA）。它的人工审议代理 (ADA) 是在最近在人工智能和计算语言学中开发的所谓神经语言模型的帮助下构建的。ADA 配备了极简主义的信念系统，可以为对话生成和提交新颖的贡献。自然语言 ABMA 允许我们用英语模拟集体审议，即用论据、理由和主张本身——而不是用它们的数学表示（如在正式模型中）。本文使用自然语言 ABMA 来测试论证的形式理性平衡模型的稳健性 [Mäs and Flache, 2013, Singer et al., 2019]：首先，只要 ADA 保持被动，确认偏差和同质性更新触发极化，这与正式模型的结果一致。然而，一旦 ADA 开始积极地产生新的贡献，守恒的演变将由作为作者的代理的属性主导。这表明，新论点、理由和主张的产生对对话产生重大影响，对于理解集体协商的动态至关重要。本文最后指出了该模型的进一步富有成效的应用以及未来研究的挑战。和主张严重影响对话，对于理解集体协商的动态至关重要。本文最后指出了该模型的进一步富有成效的应用以及未来研究的挑战。和主张严重影响对话，对于理解集体协商的动态至关重要。本文最后指出了该模型的进一步富有成效的应用以及未来研究的挑战。