In-context learning
Révision datée du 27 avril 2023 à 16:40 par Jboscher (discussion | contributions)
[1] The in-context learning (ICL) ability is formally introduced by GPT-3 : assuming that the language model has been provided with a natural language instruction and/or several task demonstrations, it can generate the expected output for the test instances by completing the word sequence of input text, without requiring additional training or gradient update
Erreur lors de la création de la vignette : Fichier manquant
Références
- [1] A Survey of Large Language Models