Unifying Structured Data as Graph for Data-to-Text Pre-Training

S Li, L Li, R Geng, M Yang, B Li, G Yuan… - Transactions of the …, 2024 - direct.mit.edu
Abstract Data-to-text (D2T) generation aims to transform structured data into natural
language text. Data-to-text pre-training has proved to be powerful in enhancing D2T …

How Well Do LLMs Identify Cultural Unity in Diversity?

J Li, J Wang, J Hu, M Jiang - arxiv preprint arxiv:2408.05102, 2024 - arxiv.org
Much work on the cultural awareness of large language models (LLMs) focuses on the
models' sensitivity to geo-cultural diversity. However, in addition to cross-cultural differences …