Login / Signup

A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More.

Zhichao WangBin BiShiva Kumar PentyalaKiran RamnathSougata ChaudhuriShubham MehrotraZixu ZhuXiang-Bo MaoSitaram AsurNa Cheng
Published in: CoRR (2024)
Keyphrases
  • image alignment
  • evolutionary algorithm
  • machine learning
  • knowledge base
  • multi agent
  • online learning
  • dynamic time warping
  • word alignment