Login / Signup

Learning to Refine with Fine-Grained Natural Language Feedback.

Manya WadhwaXinyu ZhaoJunyi Jessy LiGreg Durrett
Published in: CoRR (2024)
Keyphrases
  • fine grained
  • natural language
  • coarse grained
  • learning algorithm
  • reinforcement learning
  • learning process
  • access control
  • natural language processing
  • relevance feedback
  • massively parallel