CausalLM is not optimal for in-context learning.
Nan DingTomer LevinboimJialin WuSebastian GoodmanRadu SoricutPublished in: ICLR (2024)
Keyphrases
- learning algorithm
- prior knowledge
- learning process
- database
- supervised learning
- incremental learning
- reinforcement learning
- learning problems
- learning tasks
- online learning
- contextual information
- learning systems
- supply chain
- computer programming
- optimal control
- inductive learning
- training set
- lower bound
- decision trees
- website
- neural network
- data sets