Simple linear translators between text embedding models work only for architecturally and training-similar pairs, so embedding spaces are not universally related by such maps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How Far Do Simple Transformations Translate Across Text Embedding Models?
Simple linear translators between text embedding models work only for architecturally and training-similar pairs, so embedding spaces are not universally related by such maps.