OPTIMIZING SEQUENCES OF FEW-SHOT EXAMPLES FOR LARGE LANGUAGE MODELS

원문 (중국어)

Aspects of the present disclosure relate to automated determination of an optimized sequence of examples for few-shot learning. Embodiments include generating, via a text encoder of an embedding model, embedding representations of training examples and a query. Embodiments further include generating, via a sequence encoder of the embedding model, embedding representations of two or more sequences of the training examples based on the training example embeddings. Embodiments further include determining, based on comparing the embedding representations of the sequences to the embedding representation of the query, probabilities that each sequence of the two or more sequences is a most optimized sequence for the query. Embodiments further include modifying parameters of the embedding model through a supervised contrastive learning process that involves evaluating the determined probabilities based on a label that indicates the most optimized sequence of the two or more sequences for the query.