# US 2025/0094471 A1 · Data source curation for large language model (llm) prompts

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

- Number: US 2025/0094471 A1
- Document ID: US20250094471A1
- Status: Published application
- Kind: A1
- Application number: 18/468,679
- Filed: 2023-09-15
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Lars BRENNA; Yaw Oduro AMOATENG; Zoran HRANJ
- Web page: https://patentgrep.com/patent/US20250094471A1

## CPC

- G06F 16/345: {Summarisation for human users}
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 16/337: {Profile generation, learning or modification}
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Data source curation for large language model (LLM, generically multimodal model) prompts enables compliance with privacy requirements, while allowing for personal preferences, when Generated passages relating to a person import information from external data sources. A set of data sources is presented to a user, permitting the user to select which to use or avoid using. In some examples, when a user adds a data source, based on the nature of the data source, the user is provided a prompt to provide consent for the use of the content of that data source, enabling user-directed curation of the data sources used in the LLM generation of a summary about the person. In some examples, the set of data sources presented to a user had been previously curated according to governing policies, to restrict the user from accepting use of a data source that is disfavored for legal or policy reasons.

## Claims

### Claim 1

A system comprising:
a processor; and
a computer-readable medium storing instructions that are operative upon execution by the processor to:
present, in a first user interface (UI), a first set of data source identifications and a first set of data source selections, each data source selection of the first set of data source selections corresponding to a respective data source identification of the first set of data source identifications, the first set of data source selections indicating whether to use a data source identified by the corresponding data source identification;
detect, through the first UI, a change to the first set of data source selections;
detect a first approval, through the first UI, to generate a first generated passage using the first set of data source selections;
persist the first set of data source selections and a record of the first approval;
based on at least detecting the first approval, generate the first generated passage using each data source identified as to be used in the first set of data source selections, wherein generating the first generated passage comprises:
retrieving data from each data source identified as to be used in the first set of data source selections;
generating a multimodal model (MM) prompt including MM instructions and data retrieved from each data source identified as to be used in the first set of data source selections; and
providing the MM prompt to an MM; and
in response to receiving the first generated passage from the MM based on the provided MM prompt, display, in the first UI, the first generated passage.

### Claim 2 (depends on 1)

The system of claim 1, wherein the instructions are further operative to:
dynamically update the first generated passage in response to detecting the change to the first set of data source selections.

### Claim 3 (depends on 1)

The system of claim 1, wherein detecting the first approval to generate the first generated passage using the first set of data source selections comprises:
upon detecting a change indicating a new use of a data source, generating a user approval prompt specific to the new use.

### Claim 4 (depends on 1)

The system of claim 1, wherein the instructions are further operative to:
receive, in a second UI, restrictions on the first set of data source identifications and/or the first set of data source selections.

### Claim 5 (depends on 1)

The system of claim 1, wherein the instructions are further operative to:
present, in the first UI, a viewer class selection window, wherein the first set of data source selections is associated with a first viewer class and a second set of data source selections is associated with a second viewer class, each data source selection of the second set of data source selections corresponding to a respective data source identification of the first set of data source identifications, the second set of data source selections indicating whether to use a data source identified by the corresponding data source identification;
detect, through the first UI, changes to the second set of data source selections;
detect a second approval, through the first UI, to generate a second generated passage using the second set of data source selections;
persist a record of the second approval;
based on at least detecting the second approval, generate the second generated passage using each data source identified as to be used in the second set of data source selections; and
display, in the first UI, the second generated passage.

### Claim 6 (depends on 5)

The system of claim 5, wherein the instructions are further operative to:
persist the first generated passage;
receive a viewing request from a viewer;
receive, from the viewer, a viewer class indication;
based on at least the viewer class indication indicating the first viewer class, display, in a third UI, the first generated passage;
based on at least the viewer class indication indicating the second viewer class:
generate a third generated passage using each data source identified as to be used in the second set of data source selections; and
display, in the third UI, the third generated passage.

### Claim 7 (depends on 5)

The system of claim 5, wherein the instructions are further operative to:
based on at least predicting a threshold likelihood of receiving a viewing request from a viewer of the second viewer class:
generate a third generated passage using each data source identified as to be used in the second set of data source selections; and
cache the third generated passage for a time period; and
based on at least receiving the viewing request from the viewer of the second viewer class:
display, in a third UI, the third generated passage.

### Claim 8 (depends on 1)

The system of claim 1, wherein the instructions are further operative to:
upon generating a new generated passage in the first UI, determine a difference between the new generated passage and a prior generated passage; and
highlight, in the first UI, the difference between the new generated passage and the prior generated passage.

### Claim 9

A computer-implemented method comprising:
presenting, in a first user interface (UI), a first set of data source identifications and a first set of data source selections, each data source selection of the first set of data source selections corresponding to a respective data source identification of the first set of data source identifications, the first set of data source selections indicating whether to use a data source identified by the corresponding data source identification;
detecting, through the first UI, changes to the first set of data source selections;
detecting a first approval, through the first UI, to generate a first generated passage using the first set of data source selections;
persisting the first set of data source selections and a record of the first approval;
based on at least detecting the first approval, generating the first generated passage using each data source identified as to be used in the first set of data source selections, wherein generating the first generated passage comprises:
retrieving data from each data source identified as to be used in the first set of data source selections;
generating a multimodal model (MM) prompt including MM instructions and data retrieved from each data source identified as to be used in the first set of data source selections; and
providing the MM prompt to an MM; and
displaying, in the first UI, the first generated passage.

### Claim 10 (depends on 9)

The computer-implemented method of claim 9, further comprising:
dynamically updating the first generated passage in response to detecting the change to the first set of data source selections.

### Claim 11 (depends on 9)

The computer-implemented method of claim 9, wherein detecting the first approval to generate the first generated passage using the first set of data source selections comprises:
upon detecting a change indicating a new use of a data source, generating a user approval prompt specific to the new use.

### Claim 12 (depends on 9)

The computer-implemented method of claim 9, further comprising:
receiving, in a second UI, restrictions on the first set of data source identifications and/or the first set of data source selections.

### Claim 13 (depends on 9)

The computer-implemented method of claim 9, further comprising:
presenting, in the first UI, a viewer class selection window, wherein the first set of data source selections is associated with a first viewer class and a second set of data source selections is associated with a second viewer class, each data source selection of the second set of data source selections corresponding to a respective data source identification of the first set of data source identifications, the second set of data source selections indicating whether to use a data source identified by the corresponding data source identification;
detecting, through the first UI, changes to the second set of data source selections;
detecting a second approval, through the first UI, to generate a second generated passage using the second set of data source selections;
persisting a record of the second approval;
based on at least detecting the second approval, generating the second generated passage using each data source identified as to be used in the second set of data source selections; and
displaying, in the first UI, the second generated passage.

### Claim 14 (depends on 13)

The computer-implemented method of claim 13, further comprising:
persisting the first generated passage;
receiving a viewing request from a viewer;
receiving, from the viewer, a viewer class indication;
based on at least the viewer class indication indicating the first viewer class, displaying, in a third UI, the first generated passage;
based on at least the viewer class indication indicating the second viewer class:
generating a third generated passage using each data source identified as to be used in the second set of data source selections; and
displaying, in the third UI, the third generated passage.

### Claim 15 (depends on 13)

The computer-implemented method of claim 13, further comprising:
based on at least predicting a threshold likelihood of receiving a viewing request from a viewer of the second viewer class:
generating a third generated passage using each data source identified as to be used in the second set of data source selections; and
caching the third generated passage for a time period; and
based on at least receiving the viewing request from the viewer of the second viewer class:
displaying, in a third UI, the third generated passage.

### Claim 16 (depends on 9)

The computer-implemented method of claim 9, further comprising:
upon generating a new generated passage in the first UI, determining a difference between the new generated passage and a prior generated passage; and
highlighting, in the first UI, the difference between the new generated passage and the prior generated passage.

### Claim 17

A computer storage device having computer-executable instructions stored thereon, which, on execution by a computer, cause the computer to perform operations comprising:
presenting, in a first user interface (UI), a first set of data source identifications and a first set of data source selections, each data source selection of the first set of data source selections corresponding to a respective data source identification of the first set of data source identifications, the first set of data source selections indicating whether to use a data source identified by the corresponding data source identification;
detecting, through the first UI, changes to the first set of data source selections;
detecting a first approval, through the first UI, to generate a first generated passage using the first set of data source selections;
persisting the first set of data source selections and a record of the first approval;
based on at least detecting the first approval, generating the first generated passage using each data source identified as to be used in the first set of data source selections, wherein generating the first generated passage comprises:
retrieving data from each data source identified as to be used in the first set of data source selections;
generating a multimodal model (MM) prompt including MM instructions and data retrieved from each data source identified as to be used in the first set of data source selections; and
providing the MM prompt to an MM;
displaying, in the first UI, the first generated passage;
persisting the first generated passage;
presenting, in the first UI, a viewer class selection window, wherein the first set of data source selections is associated with a first viewer class and a second set of data source selections is associated with a second viewer class, each data source selection of the second set of data source selections corresponding to a respective data source identification of the first set of data source identifications, the second set of data source selections indicating whether to use a data source identified by the corresponding data source identification;
detecting, through the first UI, changes to the second set of data source selections;
detecting a second approval, through the first UI, to generate a second generated passage using the second set of data source selections;
persisting a record of the second approval;
based on at least detecting the second approval, generating the second generated passage using each data source identified as to be used in the second set of data source selections; and
displaying, in the first UI, the second generated passage.

### Claim 18 (depends on 17)

The computer storage device of claim 17, wherein the operations further comprise:
based on at least predicting a threshold likelihood of receiving a viewing request from a viewer of the second viewer class:
generating a third generated passage using each data source identified as to be used in the second set of data source selections; and
caching the third generated passage for a time period; and
based on at least receiving the viewing request from the viewer of the second viewer class:
displaying, in a third UI, the third generated passage.

### Claim 19 (depends on 17)

The computer storage device of claim 17, wherein the operations further comprise:
dynamically updating the first generated passage in response to detecting the change to the first set of data source selections.

### Claim 20 (depends on 17)

The computer storage device of claim 17, wherein the operations further comprise:
detecting a third approval by the user for the first generated passage;
persisting a record of the third approval;
detecting, through the first UI, selection of the second viewer class;
detecting a fourth approval by the user for the second generated passage; and
persisting a record of the fourth approval.
