Improving Mathematical Reasoning with Process Supervision

      We’ve trained a model to achieve a new state-of-the-art in mathematical problem solving by rewarding each correct step of reasoning (“process supervision”) instead of simply rewarding the correct final answer (“outcome supervision”). In addition to boosting performance relative to outcome supervision, process supervision also has an important alignment benefit: it directly trains the model to produce a chain-of-thought that is endorsed by humans. Read More OpenAI Blog 

​  


Posted

in

by

Tags:

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *