With chain-of-thought supervision, the PAC sample complexity is roughly d divided by the CoT information, which can be much larger than the target error epsilon.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
With chain-of-thought supervision, the PAC sample complexity is roughly d divided by the CoT information, which can be much larger than the target error epsilon.