LMs develop shared yet item-sensitive filler-gap mechanisms with limited data but require substantially more data than humans to match generalizations.
Based on these results, we selected a batch size of 25 with 80 training steps (2000 total samples) for all experiments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?
LMs develop shared yet item-sensitive filler-gap mechanisms with limited data but require substantially more data than humans to match generalizations.