Cultural Commonsense Knowledge for Intercultural Dialogues

TL;DR

This paper introduces MANGO, a method to extract and summarize cultural knowledge assertions from LLMs, significantly enhancing intercultural dialogue systems by providing high-quality, culturally aware responses.

Contribution

MANGO is a novel iterative prompting and consolidation approach that produces a large, high-quality resource of cultural assertions from LLMs, improving intercultural dialogue performance.

Findings

MANGO yields 167K assertions for 30K concepts and 11K cultures.

Adding MANGO's cultural assertions improves dialogue response quality.

Cultural knowledge augmentation enhances sensitivity and specificity in intercultural conversations.

Abstract

Despite recent progress, large language models (LLMs) still face the challenge of appropriately reacting to the intricacies of social and cultural conventions. This paper presents MANGO, a methodology for distilling high-accuracy, high-recall assertions of cultural knowledge. We judiciously and iteratively prompt LLMs for this purpose from two entry points, concepts and cultures. Outputs are consolidated via clustering and generative summarization. Running the MANGO method with GPT-3.5 as underlying LLM yields 167K high-accuracy assertions for 30K concepts and 11K cultures, surpassing prior resources by a large margin in quality and size. In an extrinsic evaluation for intercultural dialogues, we explore augmenting dialogue systems with cultural knowledge assertions. Notably, despite LLMs inherently possessing cultural knowledge, we find that adding knowledge from MANGO improves the overall quality, specificity, and cultural sensitivity of dialogue responses, as judged by human annotators. Data and code are available for download.