Mango
Multi-Cultural Commonsense Knowledge Distillation
Despite recent progress, large language models (LLMs) still face the challenge of appropriately reacting to the intricacies of social and cultural conventions.
We propose 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 assertions
- 30K concepts
- 11K cultures.
Our resource surpassing prior resources by a large margin in quality and size.
Further links
Publications
- Tuan-Phong Nguyen, Simon Razniewski, and Gerhard Weikum. Cultural Commonsense Knowledge for Intercultural Dialogues. CIKM 2024. [pdf]