Methods and systems for prompting large language model to generate formatted output

Patent metadata

Field	Value
Publication number	US-12561512-B2
Application number	US-202318491370-A
Country	US
Kind code	B2
Filing date	Oct 20, 2023
Priority date	Mar 14, 2023
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

The present disclosure describes a technical solution that enables a trained large language model (LLM) to generate a revised text in a manner that enables the LLM to preserve formatting that was present in the original text. When a text-editing instruction is received for a text passage having a formatting tag, the text passage is processed to identify the formatting tag in the text passage. The LLM is prompted to generate a revised text passage, using a prompt that includes the text-editing instruction and that also includes a formatting-specific instruction to format the revised text passage using the formatting tag in the revised text passage. The revised text passage is received and caused to be displayed based on the formatting tag, such that the formatting of the original text is maintained.

First claim

The invention claimed is:

1 . A system comprising:
a processing unit configured to execute computer-readable instructions to cause the system to:
receive at least one text-editing instruction related to at least a portion of a text passage having at least one formatting tag;
process the text passage to identify the at least one formatting tag in the text passage, and to identify a category of a text related to the at least one formatting tag;
generate a formatting example by:
retrieving, from a text database, an example text belonging to the identified category; and
applying the at least one formatting tag to the example text;

generate a first prompt to a large language model (LLM) to generate a revised text passage, the first prompt including the text-editing instruction related to at least the portion of the text passage, the first prompt further including a formatting-specific instruction to format the revised text passage using the at least one formatting tag in the revised text passage, the formatting-specific instruction including the formatting example;
cause the LLM to generate the revised text passage, using the first prompt as input to the LLM;
receive the revised text passage generated based on the first prompt; and
cause the revised text passage to be displayed by causing rendering of the at least one formatting tag to the revised text passage.

2 . The system of claim 1 , wherein the processing unit is configured to execute instructions to further cause the system to:
provide, to a user device, a user interface (UI) for inputting the at least one text-editing instruction and the text passage having the at least one formatting tag; wherein the at least one text-editing instruction and the text passage are received from the user device; and wherein the revised text passage is outputted to the user device and the user device is caused to display the revised text passage via the UI.

3 . The system of claim 1 , wherein the processing unit is configured to execute computer-readable instructions to further cause the system to process the text passage by:
parsing the text passage to identify the at least one formatting tag; wherein the formatting-specific instruction is included in the first prompt responsive to the at least one formatting tag being identified by the parsing.

4 . The system of claim 3 , wherein the processing unit is configured to execute computer-readable instructions to further cause the system to process the text passage by:
parsing the text passage to identify a formatting language of the at least one formatting tag; wherein the formatting-specific instruction includes the identified formatting language.

5 . The system of claim 1 , wherein the processing unit is configured to execute computer-readable instructions to further cause the system to process the text passage by:
processing the text passage using trained classifier that has been trained to classify text formatting, the trained classifier outputting a class label identifying a formatting language of the at least one formatting tag; wherein the formatting-specific instruction includes the identified formatting language.

6 . The system of claim 5 , wherein the trained classifier has been further trained to annotate formatting tags belonging to the identified formatting language, wherein the trained classifier further outputs an annotated text passage annotating the at least one formatting tag;
wherein the formatting-specific instruction further includes an instruction to format the revised text passage using the annotated at least one formatting tag in the revised text passage.

7 . The system of claim 1 , wherein the processing unit is configured to execute computer-readable instructions to further cause the system to process the text passage by:
generating a second prompt to the LLM including the text passage, the second prompt also including an instruction to cause the LLM to annotate the text passage to identify the at least one formatting tag; wherein the formatting-specific instruction includes the annotated text passage and an instruction to format the revised text passage using the annotated at least one formatting tag in the revised text passage.

8 . A method comprising:
receiving at least one text-editing instruction related to at least a portion of a text passage having at least one formatting tag; processing the text passage to identify the at least one formatting tag in the text passage, and to identify a category of a text related to the at least one formatting tag; generating a formatting example by:
retrieving, from a text database, an example text belonging to the identified category; and
applying the at least one formatting tag to the example text;
generating a first prompt to a large language model (LLM) to generate a revised text passage, the first prompt including the text-editing instruction related to at least the portion of the text passage, the first prompt further including a formatting-specific instruction to format the revised text passage using the at least one formatting tag in the revised text passage, the formatting-specific instruction including the formatting example; causing the LLM to generate the revised text passage, using the first prompt as input to the LLM; receiving the revised text passage generated based on the first prompt; and causing the revised text passage to be displayed by causing rendering of the at least one formatting tag to the revised text passage.

9 . The method of claim 8 , further comprising:
providing, to a user device, a user interface (UI) for inputting the at least one text-editing instruction and the text passage having the at least one formatting tag; wherein the at least one text-editing instruction and the text passage are received from the user device; and wherein the revised text passage is outputted to the user device and the user device is caused to display the revised text passage via the UI.

10 . The method of claim 8 , wherein processing the text passage comprises:
parsing the text passage to identify the at least one formatting tag; wherein the formatting-specific instruction is included in the first prompt responsive to the at least one formatting tag being identified by the parsing.

11 . The method of claim 10 , wherein processing the text passage comprises:
parsing the text passage to identify a formatting language of the at least one formatting tag; wherein the formatting-specific instruction includes the identified formatting language.

12 . The method of claim 8 , wherein processing the text passage comprises:
processing the text passage using trained classifier that has been trained to classify text formatting, the trained classifier outputting a class label identifying a formatting language of the at least one formatting tag; wherein the formatting-specific instruction includes the identified formatting language.

13 . The method of claim 12 , wherein the trained classifier has been further trained to annotate formatting tags belonging to the identified formatting language, wherein the trained classifier further outputs an annotated text passage annotating the at least one formatting tag;
wherein the formatting-specific instruction further includes an instruction to format the revised text passage using the annotated at least one formatting tag in the revised text passage.

14 . The method of claim 8 , wherein processing the text passage comprises:
generating a second prompt to the LLM including the text passage, the second prompt also including an instruction to cause the LLM to anno

Assignees

• Shopify Inc

Inventors

• Maschmeyer Russ
• Goligorsky David
• Beauchamp Daniel
• Michel Benjamin

Classifications

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G06F40/205

  Parsing · CPC title

• G06F40/103

  Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191) · CPC title

• G06F40/166

  Editing, e.g. inserting or deleting · CPC title

• G06F40/106 Primary

  Display of layout of documents; Previewing · CPC title