Direct Preference Optimization (DPO)

5 posts · 4 sources

Hugging FaceBlog1w

Open-sourcing AstaBrief, the fast report-generation model in Asta

Fireworks AIBlog20 Jul

Heidi x Fireworks: Bridging the Gap in Frontier Model Performance

Hugging FaceBlog17 Apr

Direct Preference Optimization Beyond Chatbots

Together AIBlog2 Feb

Fine-tuning open LLM judges to outperform GPT-5.2

CerebrasBlog5 Mar

Fine-Tuning Language Models Using Direct Preference Optimization