# US 2026/0099772 A1 · Large language model unlearning via loss adjustments

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

- Number: US 2026/0099772 A1
- Document ID: US20260099772A1
- Status: Published application
- Kind: A1
- Application number: 19/347,258
- Filed: 2025-10-01
- Published: 2026-04-09
- Earliest claimed: 2024-10-03
- Assignees: Accenture Global Solutions Limited
- Applicants: Accenture Global Solutions Limited
- Inventors: Jinlong PANG; Jiaheng WEI; Ankit Parag SHAH; Yujia BAO; Yaxuan WANG; Wei WEI; Yang LIU; Quan LIU; Yuhao LIU
- Web page: https://patentgrep.com/patent/US20260099772A1

## CPC

- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

System and method for LLM unlearning via loss adjustments are disclosed. The method includes accessing forget data samples from one or more datasets, associating a template response for each forget data sample via implementation of one or more LLMs, and training a target LLM using a forget data only loss adjustment (FLAT) function to generate an unlearned LLM, including implementing a loss adjustment to maximize a divergence for between an available template answer and a forget answer only with respect to forget data samples.

## Claims

### Claim 1

A method for implementing unlearning in large-language models (LLM) to enhance LLM performance, the method comprising:
accessing, by a processor, forget data samples from one or more datasets;
associating, by the processor, a template response for each forget data sample via implementation of one or more LLMs; and
training, by the processor, a target LLM using a forget data only loss adjustment (FLAT) function to generate an unlearned LLM, including implementing a loss adjustment to maximize a divergence for between an available template answer and a forget answer only with respect to forget data samples.

### Claim 2 (depends on 1)

The method according to claim 1, further comprising assigning, by the processor, importance weights for learning of template responses and forgetting of responses subject to unlearning.

### Claim 3 (depends on 1)

The method according to claim 1, further comprising designating, by the processor, a first unlearning rate and a second unlearning rate.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the FLAT function is represented by:
L
⁡
(
x
f
,
y
e
,
y
f
;
θ
)
=
-
[
sup
g
⁢
(
g
⁢
(
P
⁡
(
x
f
,
y
e
;
θ
)
)
-
f
*
⁢
(
g
⁢
(
P
⁡
(
x
f
,
y
f
;
θ
)
)
)
)
]
L
⁡
(
x
f
,
y
e
,
y
f
;
θ
)
=
-
g
*
⁢
(
P
⁡
(
x
f
,
y
e
;
θ
)
)
+
f
*
⁢
(
g
*
⁢
(
P
⁡
(
x
f
,
y
f
;
θ
)
)
)
.

### Claim 5 (depends on 1)

The method according to claim 1, further comprising maximizing, by the processor, a divergence for a first joint distribution and a second joint distribution.

### Claim 6

A non-transitory computer-readable storage medium having an executable stored thereon, which when executed instructs a processor to:
generate a forget data only loss adjustment (FLAT) function to provide a loss adjustment to maximize a divergence for between an available template answer and a forget answer only with respect to forget data samples; and
train a target large language model (LLM) using the FLAT function to generate an unlearned LLM, including updating node content and embedding vectors of the target LLM.

### Claim 7 (depends on 6)

The non-transitory computer-readable storage medium of claim 6, wherein the executable when executed further instructs the processor to access forget data samples from one or more datasets and associate a template response for each forget data sample via implementation of one or more LLMs.

### Claim 8 (depends on 6)

The non-transitory computer-readable storage medium of claim 6, wherein the FLAT function is to assign importance weights for learning of template responses and forgetting of responses subject to unlearning.

### Claim 9 (depends on 6)

The non-transitory computer-readable storage medium of claim 6, wherein the executable, when executed further instructs the processor to generate exemplary responses for unlearned data samples.

### Claim 10 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the FLAT function is to disregard retain data or a reference LLM in implementing response calibration.

### Claim 11 (depends on 6)

The non-transitory computer-readable storage medium of claim 6, wherein the executable when executed further instructs the processor to forget unlearned data samples with bad responses and generate good responses for unlearned data samples.

### Claim 12 (depends on 6)

The non-transitory computer-readable storage medium of claim 6, wherein the executable when executed further instructs the processor to designate a first unlearning rate and a second unlearning rate.

### Claim 13 (depends on 6)

The non-transitory computer-readable storage medium of claim 6, wherein the executable when executed further instructs the processor to maximize a divergence for a first joint distribution and a second joint distribution.

### Claim 14 (depends on 6)

The non-transitory computer-readable storage medium of claim 6, wherein training the target LLM using the FLAT function includes utilizing an unlearned data set.

### Claim 15

A system comprising:
a processor; and
a memory communicably coupled to the processor, wherein the memory comprises processor-executable instructions which, when executed by the processor, cause the processor to:
retrieve data samples from one or more datasets via implementation of one or more LLMs;
generate a forget data only loss adjustment (FLAT) function to maximize a divergence between a preferred template response and a forget response; and
associate the FLAT function with a target large language model (LLM) to generate an unlearned LLM.

### Claim 16 (depends on 15)

The system of claim 15, wherein the processor is further to assign importance weights for learning of template responses and forgetting of responses subject to unlearning.

### Claim 17 (depends on 15)

The system of claim 15, wherein the FLAT function is represented by:
L
⁡
(
x
f
,
y
e
,
y
f
;
θ
)
=
-
[
sup
g
⁢
(
g
⁢
(
P
⁡
(
x
f
,
y
e
;
θ
)
)
-
f
*
⁢
(
g
⁢
(
P
⁡
(
x
f
,
y
f
;
θ
)
)
)
)
]
L
⁡
(
x
f
,
y
e
,
y
f
;
θ
)
=
-
g
*
⁢
(
P
⁡
(
x
f
,
y
e
;
θ
)
)
+
f
*
⁢
(
g
*
⁢
(
P
⁡
(
x
f
,
y
f
;
θ
)
)
)
.

### Claim 18 (depends on 15)

The system of claim 15, wherein the processor is further to maximize a divergence for a first joint distribution and a second joint distribution.

### Claim 19 (depends on 15)

The system of claim 15, wherein the processor is further to designate a first unlearning rate and a second unlearning rate.

### Claim 20 (depends on 15)

The system of claim 15, wherein training the target LLM using the FLAT function includes utilizing an unlearned data set.
