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.
Comprendere l'apprendimento per rinforzo dal feedback umano (RLHF) per allineare i modelli linguistici. Da utilizzare per conoscere i dati sulle preferenze, la modellazione dei premi, l'ottimizzazione delle politiche o gli algoritmi di allineamento diretto come DPO. Fonte: itsmostafa/llm-engineering-skills.