Linear representations of grammaticality in neural language models
Whether neural language models (NLMs) possess the ability to distinguish strings on the basis of their grammaticality remains a debated topic in the computational linguistics literature. Existing evidence has largely relied on probability-based measures, testing whether models assign higher probabilities to grammatical than ungrammatical strings. However, probability comparisons have been criticized as a measure for grammatical knowledge based on the assumption that grammaticality is inherently entangled with likelihood. Model-assigned probability is a function of many related sentence propert
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%Evaluating J-space entropy as an error predictor across 7 datasets on Qwen3-4B [R] →
- PossiblePossibly related (embedding) · 52%Transformer →
- PossiblePossibly related (embedding) · 47%Understanding large language models demands distinguishing human projection from machine cognition - Nature →
- LinkedLinked via arxiv author · 85%Jane Li →
“Linear representations of grammaticality in neural language models”
- LinkedLinked via arxiv author · 85%Najoung Kim →
“Linear representations of grammaticality in neural language models”