Transformers learn connectivity on low-dimensional grid graphs but fail on high-dimensional grids or graphs with many disconnected components, with larger models showing better generalization on grids.
Causal parrots: Large language models may talk causality but are not causal
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Transformers Can Learn Connectivity in Some Graphs but Not Others
Transformers learn connectivity on low-dimensional grid graphs but fail on high-dimensional grids or graphs with many disconnected components, with larger models showing better generalization on grids.