PACE: Improving Prompt with Actor-Critic Editing for Large Language Model.
Yihong DongKangcheng LuoXue JiangZhi JinGe LiPublished in: CoRR (2023)
Keyphrases
- language model
- actor critic
- language modeling
- n gram
- speech recognition
- document retrieval
- probabilistic model
- information retrieval
- retrieval model
- reinforcement learning
- query expansion
- mixture model
- policy gradient
- smoothing methods
- optimal control
- temporal difference
- ad hoc information retrieval
- approximate dynamic programming
- gradient method
- average reward
- translation model
- function approximation
- neuro fuzzy
- dynamic programming