Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating long form content using large language models. Methods include obtaining a textual electronic document. Reference points are inserted at different locations within the textual electronic document to generate a referenced document. An input describing a set of proposed modifications to the textual electronic document is created. The input is submitted to the one or more LLMs. A response that includes, for each given proposed modification in the set of proposed modifications, (i) a corresponding action required to achieve the given proposed modification and (ii) one or more of the reference points specifying where the corresponding action is required to be performed to achieve the given proposed modification. Content of the textual electronic document is transformed to a revised document based on the response. The revised document is output to a client device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for iteratively generating different sections of a textual electronic document (“TED”) using one or more large language models (LLMs). In one aspect, a method comprises receiving a request to generate a TED, generating a generation schema of the TED specifying two or more sections of the TED for separate generation, inputting a first set of commands instructing one or more LLMs to generate a first set of text for a first section of the generation schema, inputting a second set of commands including at least a portion of the first set of text and instructing the LLMs to generate a second set of text for a second section of the generation schema, and creating the TED based on an aggregation of the first set of text and the second text according to the generation schema.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an immutable memory package (IMP) for use in processing a request with a large language model (LLM). In one aspect, a method comprises obtaining, by a system that is connected between a client device and one or more external large language models (LLMs), a package definition for a first IMP that includes sets of approved data with assigned fidelity settings from a client device, inserting the one or more sets of approved data into the first IMP in accordance with the assigned fidelity settings, assigning a first version indicator to the first IMP, providing the first IMP to the external LLMs, receiving a request for processing using the first IMP from the client device, and instructing, by the system, at least one external LLM to generate a response to the request using the first IMP.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a system that is connected between a client device and one or more external large language models (LLMs) that are each external to the system, a textual electronic document, inserting reference points at different locations within the textual electronic document, semantically processing the textual electronic document using a first language processing neural network with an instruction to identify different sub-portions of the textual electronic document that each correspond to a different semantic category, transforming the textual electronic document into multiple different smaller sub-documents, each complying with an input size limit of the external LLMs, receiving a document analysis request from the client device, identifying a particular smaller sub-document from among the multiple different smaller sub-documents for analysis, and providing the particular smaller sub-document as input to