【生成式AI】Finetuning vs. Prompting：對於大型語言模型的不同期待所衍生的兩…

In-context Learning:
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
https://arxiv.org/abs/2202.12837
Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers
https://arxiv.org/abs/2212.10559
Larger language models do in-context learning differently
https://arxiv.org/abs/2303.03846

Instruction Tuning:
Multitask Prompted Training Enables Zero-Shot Task Generalization
https://arxiv.org/abs/2110.08207
Finetuned Language Models Are Zero-Shot Learners
https://arxiv.org/abs/2109.01652

Can speech processing apply the idea of prompt? Please check “SpeechPrompt”.

SpeechPrompt

ga642381.github.io