# US 2026/0073122 A1 · Systems and methods for editing neural network-generated text

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073122 A1
- Document ID: US20260073122A1
- Status: Published application
- Kind: A1
- Application number: 19/041,725
- Filed: 2025-01-30
- Published: 2026-03-12
- Earliest claimed: 2024-09-12
- Assignees: Salesforce, Inc.
- Applicants: Salesforce, Inc.
- Inventors: Tuhin Chakrabarty; Philippe Laban; Chien-Sheng Wu
- Web page: https://patentgrep.com/patent/US20260073122A1

## CPC

- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 16/33295: {in dialogue systems}
- G06F 40/253: Grammatical analysis; Style critique
- G06F 40/30: Semantic analysis
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments described herein provide a method of detecting whether an input text is AI-generated using a neural network based language model. The method may include: formulating a span detection prompt including the input text and examples of problematic texts; generating, using the neural network based large language model in response to the span detection prompt, a textual spans in the input text and a category for each textual span in the plurality of textual spans; formulating an edit category prompt including the plurality of textual spans, the category for each textual span, and a plurality of example edits for each category; generating, using the neural network based large language model in response to the edit category prompt, a plurality of edited textual spans associated with the category; generating a revised sample text from the edits of the plurality of textual spans; and outputting, to a display, the revised sample text.

## Claims

### Claim 1

A method of detecting whether an input text is AI-generated using a neural network based language model, the method comprising:
formulating a span detection prompt including at least the input text and a plurality of examples of problematic texts;
generating, using the neural network based language model in response to the span detection prompt, a plurality of textual spans in the input text and a category for each textual span in the plurality of textual spans, wherein the category is selected from one or more of:
cliche;
unnecessary exposition;
purple prose;
poor sentence structure;
lack of specificity;
awkward word choice and phrasing; or
tense inconsistency;
formulating an edit category prompt including the plurality of textual spans, the category for each textual span, and a plurality of example edits for each category;
generating, using the neural network based language model in response to the edit category prompt, a plurality of edited textual spans associated with the category;
generating a revised sample text from the edits of the plurality of textual spans; and
outputting, to a display, the revised sample text.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
receiving an indication from a user to accept the edits of the plurality of textual spans; and
storing the revised sample text in a text corpus that includes the plurality of example edits.

### Claim 3 (depends on 1)

The method of claim 1, wherein the plurality of textual spans are non-overlapping in the input text.

### Claim 4 (depends on 1)

The method of claim 1, wherein the input text is edited sequentially on a per category basis.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving a user query through at an AI-based agent including neural network-based language model; and
generating, using the neural network-based language model, the input text from the user query.

### Claim 6 (depends on 1)

The method of claim 1, wherein each edit of the plurality of example edits includes a quality score indicative of writing quality.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
selecting the plurality of example edits based on the quality score associated with each example edit in the plurality of example edits.

### Claim 8

A system for detecting whether an input text is AI-generated using a neural network based language model, the system comprising:
a memory that stores a neural network based language model and a plurality of processor-executable instructions;
a communication interface that receives the input text; and
one or more hardware processors that read and execute the plurality of processor-executable instructions from the memory to perform operations comprising:
formulate a span detection prompt including at least the input text and a plurality of examples of problematic texts;
generate, using the neural network based language model in response to the span detection prompt, a plurality of textual spans in the input text and a category for each textual span in the plurality of textual spans, wherein the category is selected from one or more of:
cliche;
unnecessary exposition;
purple prose;
poor sentence structure;
lack of specificity;
awkward word choice and phrasing; or
tense inconsistency;
formulate an edit category prompt including the plurality of textual spans, the category for each textual span, and a plurality of example edits for each category;
generate, using the neural network based language model in response to the edit category prompt, a plurality of edited textual spans associated with the category;
generate a revised sample text from the edits of the plurality of textual spans; and
output, to a display, the revised sample text.

### Claim 9 (depends on 8)

The system of claim 8, the operations further comprising:
receive an indication from a user to accept the edits of the plurality of textual spans; and
store the revised sample text in a text corpus that includes the plurality of example edits.

### Claim 10 (depends on 8)

The system of claim 8, wherein the plurality of textual spans are non-overlapping in the input text.

### Claim 11 (depends on 8)

The system of claim 8, wherein the input text is edited sequentially on a per category basis.

### Claim 12 (depends on 8)

The system of claim 8, the operations further comprising:
receive a user query through at an AI-based agent including neural network-based language model; and
generate, using the neural network-based language model, the input text from the user query.

### Claim 13 (depends on 8)

The system of claim 8, wherein each edit of the plurality of example edits includes a quality score indicative of writing quality.

### Claim 14 (depends on 13)

The system of claim 13, the operations further comprising:
select the plurality of example edits based on the quality score associated with each example edit in the plurality of example edits.

### Claim 15

A non-transitory machine-readable medium comprising a plurality of machine-executable instructions which, when executed by one or more processors, are adapted to cause the one or more processors to perform operations comprising:
formulate a span detection prompt including at least an input text and a plurality of examples of problematic texts;
generate, using the neural network based language model in response to the span detection prompt, a plurality of textual spans in the input text and a category for each textual span in the plurality of textual spans, wherein the category is selected from one or more of:
cliche;
unnecessary exposition;
purple prose;
poor sentence structure;
lack of specificity;
awkward word choice and phrasing; or
tense inconsistency;
formulate an edit category prompt including the plurality of textual spans, the category for each textual span, and a plurality of example edits for each category;
generate, using the neural network based language model in response to the edit category prompt, a plurality of edited textual spans associated with the category;
generate a revised sample text from the edits of the plurality of textual spans; and
output, to a display, the revised sample text.

### Claim 16 (depends on 15)

The non-transitory machine-readable medium of claim 15, the operations further comprising:
receive an indication from a user to accept the edits of the plurality of textual spans; and
store the revised sample text in a text corpus that includes the plurality of example edits.

### Claim 17 (depends on 15)

The non-transitory machine-readable medium of claim 15, wherein the plurality of textual spans are non-overlapping in the input text.

### Claim 18 (depends on 15)

The non-transitory machine-readable medium of claim 15, wherein the input text is edited sequentially on a per category basis.

### Claim 19 (depends on 15)

The non-transitory machine-readable medium of claim 15, the operations further comprising:
receive a user query through at an AI-based agent including neural network-based language model; and
generate, using the neural network-based language model, the input text from the user query.

### Claim 20 (depends on 15)

The non-transitory machine-readable medium of claim 15, wherein each edit of the plurality of example edits includes a quality score indicative of writing quality.
