Extending machine learning model revision capabilities to long form content

A system that is connected between a client device and one or more large language models (LLMs), comprising:

• one or more memory devices;
• and
• one or more data processing apparatus configured to interact with the one or more memory devices and execute instructions that, upon execution, cause the one or more data processing apparatus to perform operations comprising:
• obtaining a textual electronic document;
• inserting reference points at different locations within the textual electronic document to generate a referenced document that includes the reference points;
• creating an input describing a set of proposed modifications to the textual electronic document, wherein the prompt includes instructions that cause the one or more LLMs to generate 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 one or more locations of the referenced document at which the corresponding action is required to be performed to achieve the given proposed modification;
• submitting the input to the one or more LLMs;
• receiving, from the one or more LLMs, the response that includes, for each given proposed modification in the set of proposed modifications, (i) the corresponding action required to achieve the given proposed modification and (ii) the one or more of the reference points specifying one or more locations of the referenced electronic document at which the corresponding action is required to be performed to achieve the given proposed modification;
• transforming content of the textual electronic document into a revised document by performing, for each given proposed modification in the set of proposed modifications, the corresponding action, required to achieve the proposed modification, at the one or more locations specified by the one or more reference points;
• and
• outputting the revised document to a client device.

One or more non-transitory computer readable medium storing instructions that, upon execution by one or more data processing apparatus of a system that is connected between a client device and one or more large language models (LLMs), cause the one or more data processing apparatus to perform operations comprising:

• obtaining a textual electronic document;
• inserting reference points at different locations within the textual electronic document to generate a referenced document that includes the reference points;
• creating an input describing a set of proposed modifications to the textual electronic document, wherein the prompt includes instructions that cause the one or more LLMs to generate 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 one or more locations of the referenced document at which the corresponding action is required to be performed to achieve the given proposed modification;
• submitting the input to the one or more LLMs;
• receiving, from the one or more LLMs, the response that includes, for each given proposed modification in the set of proposed modifications, (i) the corresponding action required to achieve the given proposed modification and (ii) the one or more of the reference points specifying one or more locations of the referenced electronic document at which the corresponding action is required to be performed to achieve the given proposed modification;
• transforming content of the textual electronic document into a revised document by performing, for each given proposed modification in the set of proposed modifications, the corresponding action, required to achieve the proposed modification, at the one or more locations specified by the one or more reference points;
• and
• outputting the revised document to a client device.