L2T pre-training adds explicit language learning tasks to standard LM training to improve linguistic competence benchmarks and accelerate skill acquisition without harming reasoning tasks.
InProceedings of the 2024 Conference on Empirical Methods in Natural Lan- guage Processing, pages 9632–9657, Miami, Florida, USA
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
-
Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks
L2T pre-training adds explicit language learning tasks to standard LM training to improve linguistic competence benchmarks and accelerate skill acquisition without harming reasoning tasks.