# US 2023/0274179 A1 · Query-driven challenge of ai bias

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

- Number: US 2023/0274179 A1
- Document ID: US20230274179A1
- Status: Published application
- Kind: A1
- Application number: 17/652,754
- Filed: 2022-02-28
- Published: 2023-08-31
- Earliest claimed: 2022-02-28
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Nicholas Tsang; Dana L. Price; Diane Chalmers; Andrew R. Freed
- Web page: https://patentgrep.com/patent/US20230274179A1

## CPC

- G06N 20/00: Machine learning
- G06F 40/205: Parsing
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 40/30: Semantic analysis
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system, program product, and method for processing challenges to potential artificial intelligence (AI) biases. The method includes injecting one or more first values associated with one or more respective variables into an AI platform, and generating, through the AI platform, one or more first outcomes. The method also includes collecting feedback with respect to the one or more outcomes, and parsing the feedback through a natural language understanding (NLU) application. The method further includes determining, subject to the parsing, one or more bias factors embedded within the AI platform.

## Claims

### Claim 1

A computer system for processing challenges to potential artificial intelligence (AI) biases comprising:
one or more processing devices;
one or more memory devices communicatively and operably coupled to the one or more processing devices;
a bias evaluation engine, at least partially resident within the one or more memory devices, configured to:
inject one or more first values associated with one or more respective variables into an AI platform;
generate, through the AI platform, one or more first outcomes;
collect feedback with respect to the one or more outcomes;
parse the feedback through a natural language understanding (NLU) application; and
determine, subject to the parsing, one or more bias factors embedded within the AI platform.

### Claim 2 (depends on 1)

The system of claim 1, wherein the bias evaluation engine is further configured to:
inject the one or more first values associated with the one or more respective variables into a machine learning (ML) model.

### Claim 3 (depends on 1)

The system of claim 1, wherein the bias evaluation engine is further configured to:
transmit the one or more first outcomes; and
generate a natural language claim of one or more biases embedded within the one or more outcomes.

### Claim 4 (depends on 1)

The system of claim 1, wherein the bias evaluation engine is further configured to:
identify at least a portion of the one or more respective variables in each of the one or more bias factors.

### Claim 5 (depends on 4)

The system of claim 4, wherein the bias evaluation engine is further configured to:
generate one or more second values for each of the one or more respective variables for each of the one or more bias factors; and
inject the one or more second values associated with the one or more respective variables into the AI platform.

### Claim 6 (depends on 5)

The system of claim 5, wherein the bias evaluation engine is further configured to:
generate, through the AI platform, one or more second outcomes.

### Claim 7 (depends on 6)

The system of claim 6, wherein the bias evaluation engine is further configured to:
produce details of the one or more second outcomes, including one or more of:
summary metrics;
comparisons with the one or more first outcomes; and
natural language explanations; and
transmit the details of the one or more second outcomes.

### Claim 8

A computer program product embodied on at least one computer readable storage medium having computer executable instructions for processing challenges to potential artificial intelligence (AI) biases, that when executed cause one or more computing devices to:
inject one or more first values associated with one or more respective variables into an AI platform;
generate, through the AI platform, one or more first outcomes;
collect feedback with respect to the one or more outcomes;
parse the feedback through a natural language understanding (NLU) application; and
determine, subject to the parsing, one or more bias factors embedded within the AI platform.

### Claim 9 (depends on 8)

The computer program product of claim 8, further having computer executable instructions to:
inject the one or more first values associated with the one or more respective variables into a machine learning (ML) model.

### Claim 10 (depends on 8)

The computer program product of claim 8, further having computer executable instructions to:
transmit the one or more first outcomes; and
generate a natural language claim of one or more biases embedded within the one or more outcomes.

### Claim 11 (depends on 8)

The computer program product of claim 8, further having computer executable instructions to:
identify at least a portion of the one or more respective variables in each of the one or more bias factors.

### Claim 12 (depends on 11)

The computer program product of claim 11 further having computer executable instructions to:
generate one or more second values for each of the one or more respective variables for each of the one or more bias factors; and
inject the one or more second values associated with the one or more respective variables into the AI platform.

### Claim 13 (depends on 12)

The computer program product of claim 12 further having computer executable instructions to:
generate, through the AI platform, one or more second outcomes.

### Claim 14

A computer-implemented method for processing challenges to potential artificial intelligence (AI) biases comprising:
injecting one or more first values associated with one or more respective variables into an AI platform;
generating, through the AI platform, one or more first outcomes;
collecting feedback with respect to the one or more outcomes;
parsing the feedback through a natural language understanding (NLU) application; and
determining, subject to the parsing, one or more bias factors embedded within the AI platform.

### Claim 15 (depends on 14)

The method of claim 14, wherein the injecting one or more first values associated with the one or more respective variables into the AI platform comprises:
injecting the one or more first values associated with the one or more respective variables into a machine learning (ML) model.

### Claim 16 (depends on 14)

The method of claim 14, wherein the collecting feedback with respect to the one or more first outcomes comprises:
transmitting the one or more first outcomes; and
generating a natural language claim of one or more biases embedded within the one or more outcomes.

### Claim 17 (depends on 14)

The method of claim 14, wherein the determining one or more bias factors comprises:
identifying at least a portion of the one or more respective variables in each of the one or more bias factors.

### Claim 18 (depends on 17)

The method of claim 17, further comprising:
generating one or more second values for each of the one or more respective variables for each of the one or more bias factors; and
injecting the one or more second values associated with the one or more respective variables into the AI platform.

### Claim 19 (depends on 18)

The method of claim 18, further comprising:
generating, through the AI platform, one or more second outcomes.

### Claim 20 (depends on 19)

The method of claim 19, further comprising:
producing details of the one or more second outcomes, including one or more of:
summary metrics;
comparisons with the one or more first outcomes; and
natural language explanations; and
transmitting the details of the one or more second outcomes.
