Improving mathematical reasoning with process supervision
- ID
- 774
- Status
- new
- Published
- 31 May 2023, 3:00 PM
- Fetched
- 27 Jun 2026, 7:47 PM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/improving-mathematical-reasoning-with-process-supervision
- Source URL
- https://openai.com/news/rss.xml
Excerpt
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.
Summary
No summary yet. It will appear after the daemon summarizes this item.