rlhf

SKILL.md

Reinforcement Learning from Human Feedback (RLHF) is a technique for aligning language models with human preferences. Rather than relying solely on next-token prediction, RLHF uses human judgment to guide model behavior toward helpful, harmless, and honest outputs.

Pretraining produces models that predict likely text, not necessarily good text. A model trained on internet data learns to complete text in ways that reflect its training distribution—including toxic, unhelpful, or dishonest patterns. RLHF addresses this gap by optimizing for human preferences rather than likelihood.

The core insight: humans can often recognize good outputs more easily than they can specify what makes an output good. RLHF exploits this by collecting human judgments and using them to shape model behavior.

Comprendre l'apprentissage par renforcement à partir de la rétroaction humaine (RLHF) pour aligner les modèles de langage. À utiliser pour découvrir les données de préférences, la modélisation des récompenses, l'optimisation des politiques ou les algorithmes d'alignement direct tels que DPO. Source : itsmostafa/llm-engineering-skills.

Voir l'original