构建对话网络数学模型，揭示错误信息传播机制并提出互评纠错方案。
A Mathematical Theory of Discursive Networks
- 将人与大模型视为平等节点，建模信息在对话网络中的流动
- 发现四种错误传播机制，自修复可导致稳定错误率
- 引入开源互评算法FOO，实现网络内相互校验，提升可信度
大型语言模型将写作转化为人与软件之间的实时互动。我们将这一新媒介定义为话语网络，将人和大模型视为平等节点，追踪其观点的传播路径。我们将错误信息的生成定义为无效性（任何事实、逻辑或结构上的失误），并揭示其受四种风险驱动：偏离真实、自我修复、全新虚构和外部检测。我们构建了一个通用的话语网络数学模型，表明仅由漂移与自我修复主导的系统会稳定在较低错误率。即使给每个错误主张赋予微小的同行评审机会，也能使系统转向以真实为主导的状态。我们通过开源的Flaws-of-Others（FOO）算法实现同行评审：一组代理在可配置循环中相互批判，再由调和者整合结论。我们识别出一种伦理失范——epithesis，即人类未参与话语网络。核心启示是实践性的：在这个新媒介中，可靠性不来自单个模型的完美，而来自将不完备模型连接成具有相互问责机制的网络。
原文摘要 · Abstract (English)
Large language models (LLMs) turn writing into a live exchange between humans and software. We characterize this new medium as a discursive network that treats people and LLMs as equal nodes and tracks how their statements circulate. We define the generation of erroneous information as invalidation (any factual, logical, or structural breach) and show it follows four hazards: drift from truth, self-repair, fresh fabrication, and external detection. We develop a general mathematical model of discursive networks that shows that a network governed only by drift and self-repair stabilizes at a modest error rate. Giving each false claim even a small chance of peer review shifts the system to a truth-dominant state. We operationalize peer review with the open-source Flaws-of-Others (FOO) algorithm: a configurable loop in which any set of agents critique one another while a harmonizer merges their verdicts. We identify an ethical transgression, epithesis, that occurs when humans fail to engage in the discursive network. The takeaway is practical and cultural: reliability in this new medium comes not from perfecting single models but from connecting imperfect ones into networks that enforce mutual accountability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。