Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment
This work addresses the need for AI systems to reason across cultures, focusing on a domain-specific gap in social norm modeling beyond American society.
The authors tackled the problem of computational modeling of social norms across cultures by proposing a method to discover and compare descriptive social norms between Chinese and American societies, resulting in a dataset of 3,069 aligned social norms and showing that existing models under 3B parameters have significant room for improvement in explainable entailment tasks.
Designing systems that can reason across cultures requires that they are grounded in the norms of the contexts in which they operate. However, current research on developing computational models of social norms has primarily focused on American society. Here, we propose a novel approach to discover and compare descriptive social norms across Chinese and American cultures. We demonstrate our approach by leveraging discussions on a Chinese Q&A platform (Zhihu) and the existing SocialChemistry dataset as proxies for contrasting cultural axes, align social situations cross-culturally, and extract social norms from texts using in-context learning. Embedding Chain-of-Thought prompting in a human-AI collaborative framework, we build a high-quality dataset of 3,069 social norms aligned with social situations across Chinese and American cultures alongside corresponding free-text explanations. To test the ability of models to reason about social norms across cultures, we introduce the task of explainable social norm entailment, showing that existing models under 3B parameters have significant room for improvement in both automatic and human evaluation. Further analysis of cross-cultural norm differences based on our dataset shows empirical alignment with the social orientations framework, revealing several situational and descriptive nuances in norms across these cultures.