Memory context for large language model classification override

Abstract

Memory context for large language model classification override performing operations including obtaining a document and initiating processing the document through a shared large language model to generate an LLM classification in a set of classifications. The operations further include processing the document through an embedding generation model to generate a value embedding for the document, comparing the value embedding with stored value embeddings for a user, and overriding, in the set of classifications, the LLM classification with a stored value classification when a corresponding stored embedding in the stored embeddings matches the value embedding. The operations further include updating a data repository with the set of classifications.