ResearchOrdinary
Embedding Models Measure in Peculiar Ways
Summary
Embedding spaces define notions of semantic similarity and distance. We study whether those embeddings reflect physical measurements of mass, distance, time and volume, which admit a unique, objective notion of semantic equivalence and distance. We find that physical measurement is only weakly modeled in the embedding space, and that instead quite peculiar measurement patterns can be observed. Further analysis indicates that embedding representations of physical measurements are strongly influenced by superficial string similarity, and recalibration of similarity does not substantially improve the alignment.
CategoryAI Research & Papers
TierOrdinary
Published
Indexed by AIQB
SourcearXiv
AIQB record IDintel-9855a9be025e27ffc1c5c237