Federated averaging of prompt embeddings from a frozen multilingual model improves accuracy on some low-resource tasks (XNLI) but not consistently on others (MasakhaNEWS).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
Federated averaging of prompt embeddings from a frozen multilingual model improves accuracy on some low-resource tasks (XNLI) but not consistently on others (MasakhaNEWS).