MINDS: A Cross-cultural Dialogue Corpus for Social Norm Classification and Adherence Detection

TL;DR

This paper introduces MINDS, a multilingual dialogue dataset, and Norm-RAG, a retrieval-augmented framework for nuanced social norm inference in multi-turn conversations, addressing cultural and contextual challenges.

Contribution

The work presents a novel multilingual dataset and a retrieval-augmented model for interpreting social norms in complex, multi-turn dialogues across cultures.

Findings

Norm-RAG improves norm detection accuracy.

MINDS dataset captures cross-cultural norm expressions.

Model demonstrates better generalization across languages.

Abstract

Social norms are implicit, culturally grounded expectations that guide interpersonal communication. Unlike factual commonsense, norm reasoning is subjective, context-dependent, and varies across cultures, posing challenges for computational models. Prior works provide valuable normative annotations but mostly target isolated utterances or synthetic dialogues, limiting their ability to capture the fluid, multi-turn nature of real-world conversations. In this work, we present Norm-RAG, a retrieval-augmented, agentic framework for nuanced social norm inference in multi-turn dialogues. Norm-RAG models utterance-level attributes including communicative intent, speaker roles, interpersonal framing, and linguistic cues and grounds them in structured normative documentation retrieved via a novel Semantic Chunking approach. This enables interpretable and context-aware reasoning about norm adherence and violation across multilingual dialogues. We further introduce MINDS (Multilingual Interactions with Norm-Driven Speech), a bilingual dataset comprising 31 multi-turn Mandarin-English and Spanish-English conversations. Each turn is annotated for norm category and adherence status using multi-annotator consensus, reflecting cross-cultural and realistic norm expression. Our experiments show that Norm-RAG improves norm detection and generalization, demonstrates improved performance for culturally adaptive and socially intelligent dialogue systems.