IP Library › Granted Patent US 12,626,067
Granted Patent B2
US 12,626,067 · App. 18/961,224 · Granted May 12, 2026

Grid-cell highlighting based on LLM attention scores

Inventor: George Sivulka (New York, NY)
Assignee: Hebbia Inc.
G06F40/35G06F16/221G06F16/243G06F16/24578G06F16/248G06F16/332G06F16/3344G06F16/338G06F16/383
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,626,067
App. No.
18/961,224
Granted
May 12, 2026
Kind
B2
Abstract

A data analytics system uses a grid-based data structure to improve the usability of LLMs in the analysis of large data sets, to synthesize information for use in other generative AI contexts, and to improve a user's ability to interface with an LLM. A grid-based data structure is a data structure or database that stores the results of column prompts applied to sources. The grid-based data structure may store the results in a relational manner. For example, a grid-based data structure may have rows that correspond to sources (e.g., documents, files, or databases) and columns that correspond to prompts. Each cell of the grid-based data structure stores the output of the column prompt applied to a source using an LLM. Thus, each column prompt may be systematically applied to each source to generate information based on the sources in an organized way.

Claims (56)

1 . A method comprising:

receiving a content item request from a client device, wherein the content item request comprises a text query to generate content;

generating a grid-based data structure comprising a set of rows and a set of columns, where each row is associated with a source of a plurality of sources and each column is associated with a column prompt, and wherein the set of rows and set of columns define a set of cells for the grid-based data structure, and wherein each of the set of cells comprises contents from applying a column prompt of a corresponding column to a source of a corresponding row using a large language model;

identifying a subset of the set of cells that relate to the text query;

generating a content item prompt based on contents of the identified subset of cells and the text query, wherein the content item prompt comprises text instructions for a large language model generate content item data for a content item based on the text query and the contents of the identified subset of cells;

transmitting the content item prompt to the large language model;

receiving a response from the large language model comprising the content item data;

generating a content item based on the content item data and the content item request; and

transmitting the content item to the client device for display to a user.

2 . The method of claim 1 , further comprising:

receiving a selection of a portion of the content item through a matrix user interface, wherein the selection identifies a portion of the content item;

accessing a set of attention scores corresponding to the portion of the content item, wherein the set of attention scores describe a relance of contents of the set of cells to the portion of the content item;

generating a cell score for each cell of the set of cells based on the set of attention scores; and

updating a matrix user interface to each of the set of cells based on the generated cell scores.

3 . The method of claim 2 , wherein the content item data comprises a plurality of output tokens and wherein generating a cell score for a cell comprises:

identifying a set of output tokens corresponding to the selected portion of the content item; and

identifying attention scores associated with the identified set of output tokens.

4 . The method of claim 3 , wherein the contents of each cell of the subset of cells comprise a set of input tokens that were input to the large language model, and wherein generating a cell score for a cell comprises:

identifying, for each input token of the cell, a subset of attention scores associated with the input token, wherein each of the subset of attention scores also corresponds to an output token of the identified set of output tokens; and

computing the cell score for the cell based on the identified subsets of attention scores for the input tokens of the cell.

5 . The method of claim 4 , wherein computing the cell score comprises:

computing an average score of the attention scores in the identified subsets of attention scores.

6 . The method of claim 1 , wherein the content item request comprises a type of content item to generate.

7 . The method of claim 6 , wherein the type of content item is one of a document, a presentation, slides, a spreadsheet, an email, a chat message, or a memorandum.

8 . The method of claim 1 , wherein the received response from the large language model comprises formatting instructions for formatting content item data within the content item.

9 . The method of claim 1 , wherein generating the content item comprises:

extracting the content item data from the response.

10 . The method of claim 1 , wherein the content item is displayed to the user in a matrix user interface.

11 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, causes the processor to perform operations comprising:

receiving a content item request from a client device, wherein the content item request comprises a text query to generate content;

generating a grid-based data structure comprising a set of rows and a set of columns, where each row is associated with a source of a plurality of sources and each column is associated with a column prompt, and wherein the set of rows and set of columns define a set of cells for the grid-based data structure, and wherein each of the set of cells comprises contents from applying a column prompt of a corresponding column to a source of a corresponding row using a large language model;

identifying a subset of the set of cells that relate to the text query;

generating a content item prompt based on contents of the identified subset of cells and the text query, wherein the content item prompt comprises text instructions for a large language model generate content item data for a content item based on the text query and the contents of the identified subset of cells;

transmitting the content item prompt to the large language model;

receiving a response from the large language model comprising the content item data;

generating a content item based on the content item data and the content item request; and

transmitting the content item to the client device for display to a user.

12 . The computer-readable medium of claim 11 , the operations further comprising:

receiving a selection of a portion of the content item through a matrix user interface, wherein the selection identifies a portion of the content item;

accessing a set of attention scores corresponding to the portion of the content item, wherein the set of attention scores describe a relance of contents of the set of cells to the portion of the content item;

generating a cell score for each cell of the set of cells based on the set of attention scores; and

updating a matrix user interface to each of the set of cells based on the generated cell scores.

13 . The computer-readable medium of claim 12 , wherein the content item data comprises a plurality of output tokens and wherein generating a cell score for a cell comprises:

identifying a set of output tokens corresponding to the selected portion of the content item; and

identifying attention scores associated with the identified set of output tokens.

14 . The computer-readable medium of claim 13 , wherein the contents of each cell of the subset of cells comprise a set of input tokens that were input to the large language model, and wherein generating a cell score for a cell comprises:

identifying, for each input token of the cell, a subset of attention scores associated with the input token, wherein each of the subset of attention scores also corresponds to an output token of the identified set of output tokens; and

computing the cell score for the cell based on the identified subsets of attention scores for the input tokens of the cell.

15 . The computer-readable medium of claim 14 , wherein computing the cell score comprises:

computing an average score of the attention scores in the identified subsets of attention scores.

16 . The computer-readable medium of claim 11 , wherein the content item request comprises a type of content item to generate.

17 . The computer-readable medium of claim 16 , wherein the type of content item is one of a document, a presentation, slides, a spreadsheet, an email, a chat message, or a memorandum.

18 . The computer-readable medium of claim 11 , wherein the received response from the large language model comprises formatting instructions for formatting content item data within the content item.

19 . The computer-readable medium of claim 11 , wherein generating the content item comprises:

extracting the content item data from the response.

20 . The computer-readable medium of claim 11 , wherein the content item is displayed to the user in a matrix user interface.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 13, 2025
From: SIVULKA, GEORGE
To: HEBBIA INC.
Reel/Frame 069835/0605 →
Continuity (3)
Provisional Application 63563117 · Mar 8, 2024
Provisional Application 63604124 · Nov 29, 2023
Related Publication 20250173350A1 · May 29, 2025
References Cited (33)
US 11829950B2 · Shah et al. · 2023 [cited by applicant]
US 12147758B1 · Thomas et al. · 2024 [cited by applicant]
US 12248751B1 · Neervannan et al. · 2025 [cited by applicant]
US 12271707B1 · Sivulka · 2025 [cited by examiner]
US 12493615B2 · Lazarev · 2025 [cited by examiner]
US 20230186025A1 · John et al. · 2023 [cited by applicant]
US 20230376900A1 · Shah et al. · 2023 [cited by applicant]
US 20240028312A1 · Gillman et al. · 2024 [cited by applicant]
US 20240126776A1 · Shmulyan · 2024 [cited by applicant]
US 20240303235A1 · Kulkarni et al. · 2024 [cited by applicant]
US 20240354584A1 · Mukherjee et al. · 2024 [cited by applicant]
US 20240362497A1 · Grenader et al. · 2024 [cited by applicant]
US 20240378375A1 · Coate et al. · 2024 [cited by applicant]
US 20240386058A1 · Thomas et al. · 2024 [cited by applicant]
US 20240419705A1 · Kotaru · 2024 [cited by applicant]
US 20240419923A1 · Chollampatt Muhammed Ashraf et al. · 2024 [cited by applicant]
US 20240420418A1 · Wu et al. · 2024 [cited by applicant]
US 20250006196A1 · Wang et al. · 2025 [cited by applicant]
US 20250013633A1 · Cho · 2025 [cited by examiner]
US 20250094703A1 · Malak et al. · 2025 [cited by applicant]
US 20250173350A1 · Sivulka · 2025 [cited by examiner]
US 20250173365A1 · Sivulka · 2025 [cited by examiner]
US 20250181841A1 · Sivulka · 2025 [cited by examiner]
US 20250217389A1 · Sanghi · 2025 [cited by examiner]
US 20250335450A1 · Ishchenko · 2025 [cited by examiner]
US 20250371041A1 · Yang · 2025 [cited by examiner]
WO WO2025042762A1 · 2025 [cited by applicant]
Prompting Is Programming: A Query Language for Large Language Models (Year: 2023). [cited by examiner]
Query Expansion by Prompting Large Language Models (Year: 2023). [cited by examiner]
PCT International Search Report and Written Opinion, PCT Application No. PCT/US2024/057543, Jan. 27, 2025, 24 pages. [cited by applicant]
United States Notice of Allowance, U.S. Appl. No. 18/961,216, Feb. 7, 2025, 10 pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 18/961,186, Feb. 24, 2025, 15 pages. [cited by applicant]
United States Notice of Allowance, U.S. Appl. No. 18/961,186, Jun. 3, 2025, eight pages. [cited by applicant]