LAGO shows that constraining alignment matrices of linguistically similar languages to be close improves few-shot cross-lingual embedding inversion accuracy over independent per-language baselines.
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
-
LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization
LAGO shows that constraining alignment matrices of linguistically similar languages to be close improves few-shot cross-lingual embedding inversion accuracy over independent per-language baselines.