Understanding interpersonal communication requires, in part, understanding the social context and norms in which a message is said. However, current methods for identifying offensive content in such communication largely operate independent of context, with only a few approaches considering community norms or prior conversation as context. Here, we introduce a new approach to identifying inappropriate communication by explicitly modeling the social relationship between the individuals. We introduce a new dataset of contextually-situated judgments of appropriateness and show that large language models can readily incorporate relationship information to accurately identify appropriateness in a given context. Using data from online conversations and movie dialogues, we provide insight into how the relationships themselves function as implicit norms and quantify the degree to which context-sensitivity is needed in different conversation settings. Further, we also demonstrate that contextual-appropriateness judgments are predictive of other social factors expressed in language such as condescension and politeness.

翻译：理解人际沟通需要部分地理解消息所传达的社会背景和规范。然而，当前识别此类沟通中冒犯性内容的方法大多独立于语境运作，仅有少数方法考虑社区规范或先前对话作为语境。本文提出一种新方法，通过显式建模个体之间的社交关系来识别不恰当的沟通。我们引入了一个新的语境化适切性判断数据集，并表明大语言模型可以轻松整合关系信息，从而在给定语境中准确识别适切性。利用在线对话和电影对话数据，我们揭示了关系本身如何作为隐式规范发挥作用，并量化了不同对话设置中语境敏感性的需求程度。此外，我们还证明语境适切性判断能够预测语言中表达的其他社会因素，如傲慢和礼貌。