A method and system for selecting context examples based on factorial latent variables and common factors.

Abstract

This invention discloses a method and system for selecting contextual examples based on factorial latent variables and common factors. By constructing a factorial latent state space, this invention performs refined modeling of task features, decoupling abstract task concepts into mutually independent latent factors. Through common-cause causal modeling, it abandons the binary causal assumption, treating the input text and output labels as observations jointly generated by latent factors. During the training phase, a fully correlated decoupling penalty term is introduced to optimize the variational lower bound, training a multi-head encoder to identify and separate each independent factor. During the inference phase, by calculating the demand distribution of the test input text in each factor space, a complementary example set covering all target factors is retrieved and combined from the candidate pool. This effectively solves the problem of biased example selection in complex context learning tasks, significantly improves the few-shot inference performance of large language models, achieves accurate example selection, and enhances the matching degree between examples and test input text.

Images