CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision

NeurIPSSpotlight2025

Authors: Awni Altabaa, Omar Montasser, John Lafferty
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Learning complex functions that involve multi-step reasoning poses a significant challenge for standard supervised learning from input-output examples…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

sample complexity chain-of-thought reasoning

← All NeurIPS 2025 Spotlight papers · Browse the whole archive