Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning.
Haokun LiuDerek TamMohammed MuqeethJay MohtaTenghao HuangMohit BansalColin RaffelPublished in: NeurIPS (2022)
Keyphrases
- fine tuning
- learning process
- general purpose
- learning systems
- neural network
- reinforcement learning
- active learning
- low level
- online learning
- learning contexts
- data sets
- fine tuned
- learning scheme
- parameter values
- context sensitive
- parameter space
- change detection
- computationally efficient
- supervised learning
- case study