Papers by Xiao Zinan
MonCulture-Eval: A Hierarchical Benchmark for Evaluating Mongolian Cultural Capabilities of Large Language Models across Scripts and Regions (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models excel at multilingual translation and instruction-following in low-resource settings like Tibetan, but lack cultural intelligence quantification. |
| Approach: | They propose a benchmark to assess the cultural intelligence of Large Language Models in Mongolia . they use a three-layer cognitive hierarchy and specialized tasks to assess their cultural intelligence . |
| Outcome: | The monCulture-Eval benchmark assesses the cultural intelligence of large language models in the Mongolian context across two writing systems and three regional sub-cultures. |