Where verifiable rewards for reasoning model training come from

Name: Where verifiable rewards for reasoning model training come from
Uploaded: 2026-09-30T14:00:04+00:00
Channel: Sebastian Raschka
Description: A calculator gives us a reference answer to check an LLM’s response. In this example, a matching final answer receives a reward of 1, and a mismatch receives 0. An excerpt from my reasoning model series: https://www.youtube.com/watch?v=Kh9mqTzjuEQ&list=PLfrHAQCRxtUs&index=1

Sebastian RaschkaCréateur · il y a 23 jours

Voir sur YouTube

A calculator gives us a reference answer to check an LLM’s response. In this example, a matching final answer receives a reward of 1, and a mismatch receives 0. An excerpt from my reasoning model series: https://www.youtube.com/watch?v=Kh9mqTzjuEQ&list=PLfrHAQCRxtUs&index=1

Discussion

Rejoignez la communauté pour réagir et poser vos questions.

Aucun message pour l'instant. Lancez la discussion !