Length generalization on a short-trained main task can be inherited from a longer-trained related auxiliary task trained jointly with it.
Exploring length generalization in large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Extrapolation by Association: Length Generalization Transfer in Transformers
Length generalization on a short-trained main task can be inherited from a longer-trained related auxiliary task trained jointly with it.