Explorerโ€บData Scienceโ€บMachine Learning
Research PaperResearchia:202609.18016

Embedding Models Measure in Peculiar Ways

Juri Opitz

Abstract

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 influen...

Submitted: September 18, 2026Subjects: Machine Learning; Data Science

Description / Details

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.


Source: arXiv:2609.20821v1 - http://arxiv.org/abs/2609.20821v1 PDF: https://arxiv.org/pdf/2609.20821v1 Original Link: http://arxiv.org/abs/2609.20821v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Sep 18, 2026
Topic:
Data Science
Area:
Machine Learning
Comments:
0
Bookmark
Embedding Models Measure in Peculiar Ways | Researchia