# US 2026/0064978 A1 · Controllable text generation optimized for fluency and metric scores

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

- Number: US 2026/0064978 A1
- Document ID: US20260064978A1
- Status: Published application
- Kind: A1
- Application number: 18/821,636
- Filed: 2024-08-30
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: Adobe Inc.
- Applicants: Adobe Inc.
- Inventors: An YAN; Zhao Song; Tong Yu; Ritwik Sinha; Raghavendra Kiran Addanki; David Arbour; Chinedu Ojukwu
- Web page: https://patentgrep.com/patent/US20260064978A1

## CPC

- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 40/30: Semantic analysis
- G06F 40/56: Natural language generation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Various disclosed embodiments are directed to controllable text generation that is optimized for natural language fluency and particular conditions, such as specific metrics. In other words, various embodiments generate text that is both fluent and predicted to meet particular metric scores. For example, various embodiments generate text that is not only concise and human-readable, but also is associated with particular user engagement metric scores, such as a high click rate or the like.

## Claims

### Claim 1

A system comprising:
at least one computer processor; and
one or more computer storage media storing computer-useable instructions that, when used by the at least one computer processor, cause the at least one computer processor to perform operations comprising:
accessing a dataset that includes a first set of natural language sequences and a respective metric associated with each natural language sequence, of the first set of natural language sequences;
based on the first set of natural language characters and the respective metric associated with each natural language sequence, generating, via a language model, a batch of natural language sequences;
encoding the batch of natural language sequences into a first text embedding that at least partially represents the batch natural language sequences;
for at least one word of each natural language sequence of the batch of natural language sequences computing a degree of deviation between a predicted distribution of a next word and a plurality of anchor points, each anchor point representing a reference distribution generated by the language model for maintaining natural language fluency; and
based on at least one metric of the respective metric and the degree of deviation between the predicted distribution of the next word and the plurality of anchor points, changing the input text embedding into a second text embedding.

### Claim 2 (depends on 1)

The system of claim 1, wherein the changing is based on assigning a low gradient to most positions in the first text embedding and introducing a periodic weighted factor that controls the changing at each position of the first text embedding when generating the second text embedding.

### Claim 3 (depends on 2)

The system of claim 2, wherein the first text embedding is represented by a matrix of columns and rows, each column represents a distribution of tokens, and wherein the periodic weighted factor changes one or two columns and leaves the rest of the columns unchanged in the matrix when generating the second text embedding, and wherein the changing of one or more two columns is indicative of changing one or two words in the first text embedding.

### Claim 4 (depends on 1)

The system of claim 1, wherein the computing of the degree of deviation between the predicted distribution of the next word and the plurality of anchor points is based on computing batched Kullback-Leibler (KL) Divergence, and wherein the degree of deviation is computed using KL divergence for each context t and each natural language sequence i in the batch, and wherein the batched KL divergence is an average or sum of the KL divergences across all of the natural language sequences and positions in the batch of natural language sequences.

### Claim 5 (depends on 1)

The system of claim 1, wherein the respective metric associated with each natural language sequence includes at least one of: a sentiment value, an attractiveness value, a popularity value, a quantity of clicks, a click-through rate (CTR), a conversion rate, an open rate, engagement time, a bounce rate, social media shares and likes, an email response rate, a form completion rate, and a user feedback and rating.

### Claim 6 (depends on 1)

The system of claim 1, wherein the changing is based on using an energy-based model that minimizes an energy function for the changing of the first text embedding to the second text embedding, and wherein the minimizing the energy function includes generating natural language text that optimized for a metric while remaining fluent.

### Claim 7 (depends on 1)

The system of claim 1, wherein each natural language sequence of the batch of natural language sequences represents a respective sentence.

### Claim 8 (depends on 1)

The system of claim 1, wherein the generating of the batch of natural language sequence is based on computing, via a value model, a metric score for each natural language sequence of the batch of natural language sequences the metric score being indicative of how well a respective natural language sequence of the batch of natural language sequences is expected to perform according to a given metric, and wherein the changing of the first text embedding to the second text embedding is further based on the metric score.

### Claim 9 (depends on 1)

The system of claim 1, wherein the changing of the first text embedding to the second text embedding is further based on training a value model to predict, via a scoring function, metric scores with text as input and taking gradients of the scoring function with an additional fluency constraint.

### Claim 10

A computer-implemented method comprising:
encoding a plurality of natural language sequences into a first text embedding that at least partially represents the plurality of natural language sequences;
computing, via a value model, a metric score for each natural language sequence, of the plurality of natural language sequences, the metric score being indicative of how well a respective natural language sequence is expected to perform according to a given metric;
use a periodic weighted factor that controls a change at each position of the first text embedding; and
based on the computing of the metric score for each natural language sequence, of the plurality of natural language sequences and the introducing of the periodic weighted factor, changing at least one natural language sequence, of the plurality of natural language sequences, by changing at least one word.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, wherein the first text embedding is represented by a matrix of columns and rows, each column represents a distribution of tokens, and wherein the periodic weighted factor changes one or two columns and leaves the rest of the columns unchanged in the matrix, and wherein the changing of one or more two columns is indicative of the changing of the at least one natural language sequence.

### Claim 12 (depends on 10)

The computer-implemented method of claim 10, wherein the changing is further based on computing a degree of deviation between a predicted distribution of a next word and a plurality of anchor points, each anchor point representing a reference distribution generated by the language model for maintaining natural language fluency.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, wherein the computing of the degree of deviation between the predicted distribution of the next word and the plurality of anchor points is based on computing batched Kullback-Leibler (KL) Divergence, and wherein the degree of deviation is computed using KL divergence for each context t and each natural language sequence i, and wherein the batched KL divergence is an average or sum of the KL divergences across all of the natural language sequences and positions in the plurality of natural language sequences.

### Claim 14 (depends on 10)

The computer-implemented method of claim 10, wherein the given metric includes at least one of: a sentiment value, an attractiveness value, a popularity value, a quantity of clicks, a click-through rate (CTR), a conversion rate, an open rate, engagement time, a bounce rate, social media shares and likes, an email response rate, a form completion rate, and a user feedback and rating.

### Claim 15 (depends on 10)

The computer-implemented method of claim 10, wherein the changing is further based on using an energy-based model that minimizes an energy function for the changing of the first text embedding to a second text embedding, and wherein the minimizing the energy function includes generating natural language text that optimized for a metric while remaining fluent.

### Claim 16 (depends on 10)

The computer-implemented method of claim 10, wherein each natural language sequence, of the plurality of natural language sequences, represents a respective sentence.

### Claim 17 (depends on 10)

The computer-implemented method of claim 10, further comprising training the value model to predict, via a scoring function, metric scores with text as input and taking gradients of the scoring function with an additional fluency constraint.

### Claim 18

A system comprising:
a language model means for receiving a metric value model as a scoring function and a text prompt as input, the language model generating a set of candidate text sequences;
wherein the language model means is further for converting the candidate text sequences into a text embedding; and
an energy-based model means for changing the text embedding based on at least one of: taking gradients of the scoring function with one or more constraints or using a periodic weighted factor to control whether there is a change at each token position of the text embedding.

### Claim 19 (depends on 18)

The system of claim 18, further comprising:
a metric value model means for providing the metric value model a dataset as input into the metric value model, wherein the metric value model predicting one or more metric scores.

### Claim 20 (depends on 18)

The system of claim 18, wherein the dataset include text-metric score pair scores.
