# US 2026/0087164 A1 · System and method for vector-based verification of generative ai outputs

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

- Number: US 2026/0087164 A1
- Document ID: US20260087164A1
- Status: Published application
- Kind: A1
- Application number: 18/897,516
- Filed: 2024-09-26
- Published: 2026-03-26
- Earliest claimed: 2024-09-26
- Assignees: Wells Fargo Bank, N.A.
- Applicants: Wells Fargo Bank, N.A.
- Inventors: Rameshchandra Bhaskar Ketharaju; Anjeet Kumar; Naveen Rathani; Shuvam Sengupta; Tapan Totla
- Web page: https://patentgrep.com/patent/US20260087164A1

## CPC

- G06F 21/6227: {where protection concerns the structure of data, e.g. records, types, queries}
- G06F 21/84: output devices, e.g. displays or monitors
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method may include receiving, using a processing unit, a prompt for a generative artificial intelligence model from a computing device; identifying, using the processing unit, an entity in the prompt; querying a knowledge graph for verified information associated with the entity; inputting, using the processing unit, the prompt into the generative artificial intelligence model; in response to the inputting, receiving a generated response from the generative artificial intelligence model; generating a similarity value between the generated response and the verified information; determining that the similarity value is below a threshold similarity; and based on the determining, preventing a display of the generated response.

## Claims

### Claim 1

A method comprising:
receiving, using a processing unit, a prompt for a generative artificial intelligence model from a computing device;
identifying, using the processing unit, an entity in the prompt;
querying a knowledge graph for verified information associated with the entity;
inputting, using the processing unit, the prompt into the generative artificial intelligence model;
in response to the inputting, receiving a generated response from the generative artificial intelligence model;
generating a similarity value between the generated response and the verified information;
determining that the similarity value is below a threshold similarity; and
based on the determining, preventing a display of the generated response.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
inputting, using the processing unit, the prompt into an entity recognition model;
in response to the inputting, receiving an output from the entity recognition model, the output identifying a set of entities in the prompt and a weight for each entity in the set of entities, the weight associated with an importance of the entity relative to other entities in the set of entities in the prompt; and
selecting the entity from the set of entities based on the weight of the entity.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
calculating an entity ambiguity score for the entity;
determining the entity ambiguity score exceeds a threshold;
based on the entity ambiguity score exceeding the threshold, transmitting a prompt requesting additional information about the entity; and
receiving the additional information.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
prior to the inputting, automatically modifying the prompt based on the received additional information.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
prior to the inputting, calculating a creative intent value of the prompt;
determining the creative intent value exceeds a threshold; and in response:
transmitting a response to the computing device requesting an update to the prompt;
receiving the update to the prompt; and
inputting the updated prompt into the generative artificial intelligence model.

### Claim 6 (depends on 1)

The method of claim 1, wherein the knowledge graph is configured to store verified information about entities across multiple categorical dimensions.

### Claim 7 (depends on 6)

The method of claim 6, wherein querying the knowledge graph for verified information associated with the entity includes querying the knowledge graph for verified information of the entity for a geographic dimension and temporal dimension of the multiple categorical dimensions.

### Claim 8 (depends on 7)

The method of claim 7, wherein generating the similarity value between the generated response and the verified information includes:
calculating a cosine similarity value based on the verified information of the entity for the geographic dimension and the generated response; and
calculating a cosine similarity value based on the verified information of the entity for the temporal dimension and the generated response.

### Claim 9 (depends on 6)

The method of claim 6, wherein the knowledge graph is stored in a graph database format.

### Claim 10

A non-transitory computer-readable medium comprising instructions, which when executed by a processing unit, configure the processing unit to perform operations comprising:
receiving a prompt for a generative artificial intelligence model from a computing device;
identifying an entity in the prompt;
querying a knowledge graph for verified information associated with the entity;
inputting the prompt into the generative artificial intelligence model;
in response to the inputting, receiving a generated response from the generative artificial intelligence model;
generating a similarity value between the generated response and the verified information;
determining that the similarity value is below a threshold similarity; and
based on the determining, preventing a display of the generated response.

### Claim 11 (depends on 10)

The non-transitory computer-readable medium of claim 10, wherein the instructions, which when executed by the processing unit, further configure the processing unit to perform operations comprising:
inputting the prompt into an entity recognition model;
in response to the inputting, receiving an output from the entity recognition model, the output identifying a set of entities in the prompt and a weight for each entity in the set of entities, the weight associated with an importance of the entity relative to other entities in the set of entities in the prompt; and
selecting the entity from the set of entities based on the weight of the entity.

### Claim 12 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the instructions, which when executed by the processing unit, further configure the processing unit to perform operations comprising:
calculating an entity ambiguity score for the entity;
determining the entity ambiguity score exceeds a threshold;
based on the entity ambiguity score exceeding the threshold, transmitting a prompt requesting additional information about the entity; and
receiving the additional information.

### Claim 13 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein the instructions, which when executed by the processing unit, further configure the processing unit to perform operations comprising:
prior to the inputting, automatically modifying the prompt based on the received additional information.

### Claim 14 (depends on 10)

The non-transitory computer-readable medium of claim 10, wherein the instructions, which when executed by the processing unit, further configure the processing unit to perform operations comprising:
prior to the inputting, calculating a creative intent value of the prompt;
determining the creative intent value exceeds a threshold; and in response:
transmitting a response to the computing device requesting an update to the prompt;
receiving the update to the prompt; and
inputting the updated prompt into the generative artificial intelligence model.

### Claim 15 (depends on 10)

The non-transitory computer-readable medium of claim 10, wherein the knowledge graph is configured to store verified information about entities across multiple categorical dimensions.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein querying the knowledge graph for verified information associated with the entity includes querying the knowledge graph for verified information of the entity for a geographic dimension and temporal dimension of the multiple categorical dimensions.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein generating the similarity value between the generated response and the verified information includes:
calculating a cosine similarity value based on the verified information of the entity for the geographic dimension and the generated response; and
calculating a cosine similarity value based on the verified information of the entity for the temporal dimension and the generated response.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the knowledge graph is stored in a graph database format.

### Claim 19

A system comprising:
a processing unit; and
a storage device comprising instructions, which when executed by the processing unit configure the processing unit to perform operations comprising:
receiving a prompt for a generative artificial intelligence model from a computing device;
identifying an entity in the prompt;
querying a knowledge graph for verified information associated with the entity;
inputting the prompt into the generative artificial intelligence model;
in response to the inputting, receiving a generated response from the generative artificial intelligence model;
generating a similarity value between the generated response and the verified information;
determining that the similarity value is below a threshold similarity; and
based on the determining, preventing a display of the generated response.

### Claim 20 (depends on 19)

The system of claim 19, wherein the instructions, which when executed by the processing unit, further configure the processing unit to perform operations comprising:
inputting the prompt into an entity recognition model;
in response to the inputting, receiving an output from the entity recognition model, the output identifying a set of entities in the prompt and a weight for each entity in the set of entities, the weight associated with an importance of the entity relative to other entities in the set of entities in the prompt; and
selecting the entity from the set of entities based on the weight of the entity.
