Grammaticality is linearly decodable from language model sentence representations and generalizes across phenomena and languages in larger models.
hub
year = 1971
1 Pith paper cite this work, alongside 1,205 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1,205
external citations · OpenAlex
hub tools
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Linear representations of grammaticality in neural language models
Grammaticality is linearly decodable from language model sentence representations and generalizes across phenomena and languages in larger models.