Pretrained language models score near random on a new Wikidata-derived symmetry and antisymmetry NLI task, while encoder retraining with a symmetry-aware distance reaches 100% on the task with as few as 48 training samples.
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
-
Capturing Symmetry and Antisymmetry in Language Models through Symmetry-Aware Training Objectives
Pretrained language models score near random on a new Wikidata-derived symmetry and antisymmetry NLI task, while encoder retraining with a symmetry-aware distance reaches 100% on the task with as few as 48 training samples.