A task that decomposes into a chain of atomic operations can, in theory and in Transformer experiments with chain-of-thought, be generalized from about D log D training tasks to all D^T tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?
A task that decomposes into a chain of atomic operations can, in theory and in Transformer experiments with chain-of-thought, be generalized from about D log D training tasks to all D^T tasks.