Improving mathematical reasoning with process supervision
3y
- Published
- Collected
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…
overfeed.news indexes and links. We publish a short excerpt — the full article stays at OpenAI News.
More from OpenAI News
Log in to follow this source
Advancing Coding in Low-Resource Programming Languages
Learn how OpenAI is improving ChatGPT across low-resource programming languages, with new evaluations for software engineering, SQLite, and COBOL migration.
How Itaú is building generative AI for its entire customer base
With ia.i, a conversational interface, and the IARA governance platform, Itaú is applying its AI First strategy to customers and employees — in one of Brazil’s most regulated sectors.
Benefit Street Partners answers questions faster with Codex
Anant Kumar builds tools to compare loan valuations and analyze credit agreements, using Codex for code review and faster follow-ups.
Stack Overflow for Agents triples signups with ChatGPT plugin
Two engineers shipped Stack Overflow for Agents in a few weeks with Codex, and its ChatGPT plugin helped drive up to 10× growth in agent creation.