AUTO EXAM BUILDER
A computer system for automatically building an exam displays an automated exam-building interface. The automated exam-building interface comprises a first portion of a user interface configured to display at least a portion of text data and a second portion of the user interface configured to display a question and a proposed answer based upon a selected subset of the text data. The computer system receives a selection of a first subset of the text data. The computer system creates a first task by combining the first subset of the text data with a first request and then provides the first task to a large language model. The computer system receives from the large language model a first question and a first proposed answer. The computer system displays the first question and the first proposed answer within the second portion of the user interface.
1 . A computer system for automatically building an exam, the computer system comprising:
one or more processors; and
one or more computer-readable media having stored thereon executable instructions that when executed by the one or more processors configure the computer system to perform at least the following:
display an automated exam-building interface, the automated exam-building interface comprising:
a first portion of a user interface configured to display at least a portion of text data that has been parsed from a digital document, and
a second portion of the user interface configured to display a question and a proposed answer based upon a selected subset of the text data that is being displayed within the first portion of the user interface;
identify a first chunk of the text data, wherein the first chunk is identified by receiving a selection of a first subset of the text data displayed on the first portion the user interface;
create a first task by combining the first chunk with a first request;
provide the first task to a large language model;
receive from the large language model a first question and a first proposed answer based upon the first task; and
display the first question and the first proposed answer within the second portion of the user interface.
2 . The computer system of claim 1 , wherein the first portion of a user interface is rendered in a column adjacent to the second portion of the user interface.
3 . The computer system of claim 2 , wherein the executable instructions include instructions that are executable to configure the computer system to:
receive a user selection of the first question within the second portion of the user interface; and
render a visual indication indicating the first subset of the text data within the first portion of the user interface.
4 . The computer system of claim 1 , wherein the executable instructions include instructions that are executable to configure the computer system to:
display one or more editable fields for the first question and the first proposed answer within the second portion of the user interface;
receive user input revising the first question and/or the first proposed answer; and
train the large language model using the revised first question and/or the revised first proposed answer and the first subset of the text data.
5 . The computer system of claim 4 , wherein the first proposed answer comprises multiple-choice answers, the multiple-choice answers comprising a proposed correct answer and multiple proposed incorrect answers.
6 . The computer system of claim 5 , wherein the executable instructions include instructions that are executable to configure the computer system to:
receive user input revising an incorrect answer selected from the multiple proposed incorrect answers; and
train the large language model using the revised incorrect answer and the first subset of the text data.
7 . The computer system of claim 1 , wherein the executable instructions include instructions that are executable to configure the computer system to:
identify a second chunk of the text data, wherein the second chunk is identified by receiving a selection of a second subset of the text data displayed on the first portion the user interface;
create a second task by combining the second chunk with a second request;
generate, using the large language model, a second question and a second proposed answer based upon the second task; and
display the second question and the second proposed answer within the second portion of the user interface.
8 . The computer system of claim 7 , wherein the first subset of the text data and the second subset of the text data at least partially overlap.
9 . The computer system of claim 7 , wherein first second question is a multiple-choice question and the second question is an open-ended question.
10 . A computer-implemented method for automatically building an exam, the computer-implemented method comprising:
displaying an automated exam-building interface, the automated exam-building interface comprising:
a first portion of a user interface configured to display at least a portion of text data that has been parsed from a digital document, and
a second portion of the user interface configured to display a question and a proposed answer based upon a selected subset of the text data that is being displayed within the first portion of the user interface;
identifying a first chunk of the text data, wherein the first chunk is identified by receiving a selection of a first subset of the text data displayed on the first portion the user interface;
creating a first task by combining the first chunk with a first request;
providing the first task to a large language model;
receiving from the large language model a first question and a first proposed answer based upon the first task; and
displaying the first question and the first proposed answer within the second portion of the user interface.
11 . The computer-implemented method of claim 10 , wherein the first portion of a user interface is rendered in a column adjacent to the second portion of the user interface.
12 . The computer-implemented method of claim 11 , further comprising:
receiving a user selection of the first question within the second portion of the user interface; and
rendering a visual indication indicating the first subset of the text data within the first portion of the user interface.
13 . The computer-implemented method of claim 10 , further comprising:
displaying one or more editable fields for the first question and the first proposed answer within the second portion of the user interface;
receiving user input revising the first question and/or the first proposed answer; and
training the large language model using the revised first question and/or the revised first proposed answer and the first subset of the text data.
14 . The computer-implemented method of claim 13 , wherein the first proposed answer comprises multiple-choice answers, the multiple-choice answers comprising a proposed correct answer and multiple proposed incorrect answers.
15 . The computer-implemented method of claim 14 , further comprising:
receiving user input revising an incorrect answer selected from the multiple proposed incorrect answers; and
training the large language model using the revised incorrect answer and the first subset of the text data.
16 . The computer-implemented method of claim 10 , further comprising:
identifying a second chunk of the text data, wherein the second chunk is identified by receiving a selection of a second subset of the text data displayed on the first portion the user interface;
creating a second task by combining the second chunk with a second request;
generating, using the large language model, a second question and a second proposed answer based upon the second task; and
displaying the second question and the second proposed answer within the second portion of the user interface.
17 . The computer-implemented method of claim 16 , wherein the first subset of the text data and the second subset of the text data at least partially overlap.
18 . The computer-implemented method of claim 17 , wherein first second question is a multiple-choice question and the second question is an open-ended question.
19 . A computer-readable media comprising one or more physical non-transitory computer-readable storage media having stored thereon computer-executable instructions that, when executed at a processor, cause a computer system to perform a method for automatically building an exam, the method comprising:
displaying an automated exam-building interface, the automated exam-building interface comprising:
a first portion of a user interface configured to display at least a portion of text data that has been parsed from a digital document, and
a second portion of the user interface configured to display a question and a proposed answer based upon a selected subset of the text data that is being displayed within the first portion of the user interface;
identifying a first chunk of the text data, wherein the first chunk is identified by receiving a selection of a first subset of the text data displayed on the first portion the user interface;
creating a first task by combining the first chunk with a first request;
providing the first task to a large language model;
receiving from the large language model a first question and a first proposed answer based upon the first task; and
displaying the first question and the first proposed answer within the second portion of the user interface.
20 . The computer-readable media of claim 19 , the method further comprising:
identifying a second chunk of the text data, wherein the second chunk is identified by receiving a selection of a second subset of the text data displayed on the first portion the user interface;
creating a second task by combining the second chunk with a second request;
generating, using the large language model, a second question and a second proposed answer based upon the second task; and
displaying the second question and the second proposed answer within the second portion of the user interface.