Also known as: Auto regressive Model
Un modelo autorregresivo genera o predice cada salida condicionándola a sus propias salidas previas o a elementos anteriores de una secuencia. En el modelado del lenguaje, un modelo autorregresivo predice el siguiente token a partir de los tokens precedentes y luego repite el proceso paso a paso. Muchos modelos de lenguaje grandes basados en Transformer utilizan este enfoque para la generación de texto.
A model that infers a prediction based on its own previous predictions. For example, auto-regressive language models predict the next token based on the previously predicted tokens. All Transformer-based large language models are auto-regressive. In contrast, GAN-based image models are usually not auto-regressive since they generate an image in a single forward-pass and not iteratively in steps. However, certain image generation models are auto-regressive because they generate an image in steps.