Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints

通过非暴力沟通约束减少大语言模型对话中的冲突升级

Abstract: Large language models (LLMs) are increasingly used in emotionally charged situations involving interpersonal conflict, frustration, and distress. While prior safety research has focused on preventing explicit harms such as toxic or policy-violating content, less attention has been paid to conversational behaviors that may unintentionally escalate conflict.

摘要： 大语言模型（LLM）正越来越多地被应用于涉及人际冲突、挫折和痛苦等情绪激动的场景中。尽管此前的安全研究主要集中在防止有毒内容或违反政策内容等显性危害上，但对于那些可能无意中加剧冲突的对话行为，关注度却相对较低。

In this paper, we investigate whether LLMs can be guided toward more de-escalating dialogue behavior through lightweight prompt-level constraints derived from Nonviolent Communication (NVC). We reformulate NVC principles as process-oriented guidelines that discourage blame attribution, emphasize attention to users’ emotional experiences, and encourage clarification before advice.

在本文中，我们研究了是否可以通过源自“非暴力沟通”（NVC）的轻量级提示词约束，引导大语言模型表现出更具缓和冲突倾向的对话行为。我们将非暴力沟通原则重新表述为以过程为导向的准则，旨在抑制指责归因，强调对用户情绪体验的关注，并鼓励在提供建议前先进行澄清。

Using a dual-agent simulation framework across multiple instruction-tuned models and user resistance levels, we show that NVC-constrained prompting consistently reduces conversational escalation and stabilizes interactions with highly resistant users. These results suggest that simple communication constraints can meaningfully improve the trustworthiness of LLM dialogue in conflict-prone settings.

通过在多个指令微调模型和不同用户抵触水平下使用双智能体模拟框架，我们证明了基于非暴力沟通的提示词约束能够持续减少对话冲突的升级，并稳定与高抵触情绪用户的互动。这些结果表明，简单的沟通约束可以显著提高大语言模型在易引发冲突场景下的对话可信度。