A

alignment

🔧🔗https://github.com/xinjli/alqalign multilingual speech aligner

https://github.com/princeton-nlp/SimPO SimPO: Simple Preference Optimization with a Reference-Free Reward

🔧🔗https://github.com/MultiTonic/dark-distill

A 😈😈 Dark ⚗️ AI Feedback framework for scalable LLM alignment