# Natural-Language Multi-Agent Simulations of Argumentative Opinion Dynamics

arXiv: https://arxiv.org/abs/2104.06737 · HTML: https://mlsanity.com/paper/2104.06737/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 62 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2](https://mlsanity.com/paper/2103.13033/) (2021)
- [An argumentative agent-based model of scientific inquiry](https://mlsanity.com/paper/1612.04432/) (2016)
- [An Argument Communication Model of Polarization and Ideological Alignment](https://mlsanity.com/paper/1809.06134/) (2018)

## Built on by (most cited first, 5 of 5)

- [Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena](https://mlsanity.com/paper/2310.05746/) (2023)
- [Blind Judgement: Agent-Based Supreme Court Modelling With GPT](https://mlsanity.com/paper/2301.05327/) (2023)
- [Synthetic Social Media Influence Experimentation via an Agentic Reinforcement Learning Large Language Model Bot](https://mlsanity.com/paper/2411.19635/) (2024)
- [Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models](https://mlsanity.com/paper/2509.06858/) (2025)
- [Artificial Utopia: Simulation and Intelligent Agents for a Democratised Future](https://mlsanity.com/paper/2503.07364/) (2025)

## Abstract (arXiv)

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 [Maes & 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.