🚀NEW LABGetting Started with Claude AgentsStart lab
Reasoning · Data

A Theoretical Understanding of CoT

First page
A Theoretical Understanding of CoT
Paper summary

finds that adding correct and incorrect reasoning paths in demonstrations improves the accuracy of intermediate steps and CoT; the proposed method, Coherent CoT, significantly improves performance on several benchmarks; in the Tracking Shuffled Objects dataset, Gemini Pro shows a 6.60% improvement (from 58.20% to 64.80%), and in Penguins in a Table, DeepSeek 67B demonstrates an increase of 6.17% (from 73.97% to 80.14%).

Ask this paper

Every Monday
Get next week’s papers.
Subscribe on Substack