Search Results for author:
Found 4 papers, 2 papers with code
Early Period of Training Impacts Out-of-Distribution Generalization
Prior research has found that differences in the early period of neural network training significantly impact the performance of in-distribution (ID) tasks.
Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings
Large language models (LLMs) are highly adept at question answering and reasoning tasks, but when reasoning in a situational context, human expectations vary depending on the relevant cultural common ground.
FUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing
Our experiments reveal that scheduled unfreezing induces different learning dynamics compared to standard fine-tuning, and provide evidence that the dynamics of Fisher Information during training correlate with cross-lingual generalization performance.
One does not fit all! On the Complementarity of Vision Encoders for Vision and Language Tasks
While many VEs -- of different architectures, trained on different data and objectives -- are publicly available, they are not designed for the downstream V+L tasks.
