用于对话文化语境落地的LLM-人类流水线
LLM-Human Pipeline for Cultural Context Grounding of Conversations
AI总结：
本文针对NLP模型难以理解跨文化社会规范的问题，提出对话“文化语境模式”，利用LLM与人类在环框架构建包含约11万条规范描述的中文对话数据集，显著提升了情感、情感倾向及对话行为等下游任务的性能。
摘要：
对话通常遵循因文化而异且被广泛理解的社会规范。例如，在西方“直呼父母姓名”很常见，但在大多数亚洲文化中却很少见。遵守或违反此类规范往往决定了对话的基调。人类能够非常熟练地应对需要文化意识的社会情境。然而，这对NLP模型来说是一项艰巨的任务。在本文中，我们通过为对话引入“文化语境模式”来解决这一问题。它包含（1）对话信息，如情感、对话行为等，以及（2）文化信息，如社会规范、违规等。我们使用LLMs为来自中国文化的约2.3万段对话生成了约11万条社会规范与违规描述。我们使用自动化验证策略对其进行完善，并根据具有文化意识的人类判断进行评估。我们利用交互式人类在环框架，将这些描述组织成我们称之为“规范概念”的有意义结构。我们使用符号标注将规范概念和描述落实到对话中。最后，我们将获得的数据集用于情感、情感倾向和对话行为检测等下游任务。我们证明它显著提升了经验性能。
英文摘要：
Conversations often adhere to well-understood social norms that vary across cultures. For example, while "addressing parents by name" is commonplace in the West, it is rare in most Asian cultures. Adherence or violation of such norms often dictates the tenor of conversations. Humans are able to navigate social situations requiring cultural awareness quite adeptly. However, it is a hard task for NLP models. In this paper, we tackle this problem by introducing a "Cultural Context Schema" for conversations. It comprises (1) conversational information such as emotions, dialogue acts, etc., and (2) cultural information such as social norms, violations, etc. We generate ~110k social norm and violation descriptions for ~23k conversations from Chinese culture using LLMs. We refine them using automated verification strategies which are evaluated against culturally aware human judgements. We organize these descriptions into meaningful structures we call "Norm Concepts", using an interactive human-in-loop framework. We ground the norm concepts and the descriptions in conversations using symbolic annotation. Finally, we use the obtained dataset for downstream tasks such as emotion, sentiment, and dialogue act detection. We show that it significantly improves the empirical performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
