PACE: Improving Prompt with Actor-Critic Editing for Large Language Model.
Yihong DongKangcheng LuoXue JiangZhi JinGe LiPublished in: ACL (Findings) (2024)
Keyphrases
- language model
- actor critic
- language modeling
- n gram
- information retrieval
- document retrieval
- probabilistic model
- reinforcement learning
- speech recognition
- retrieval model
- query expansion
- optimal control
- mixture model
- temporal difference
- approximate dynamic programming
- smoothing methods
- policy gradient
- translation model
- neuro fuzzy
- ad hoc information retrieval
- least squares
- policy iteration
- function approximation
- gradient method
- machine learning
- unsupervised learning
- training data