SYSTEMS AND METHODS FOR IMPROVING TEXTUAL DESCRIPTIONS USING LARGE LANGUAGE MODELS
A textual description that includes a body of unstructured text is received. Using a rating model configured to output a rating based on a degree of similarity of the received textual description and each of a set of selected textual descriptions, a rating is generated based on the received textual description. The rating model to also used to generate a suggested modification of the received textual description that, when applied to the received textual descriptions, changes the rating of the received textual description. An indication of the suggested modification can be output to a user.
1 . A computer-implemented method comprising:
obtaining, using a large language model, a textual description that includes a body of unstructured text;
generating a rating based on the obtained textual description using a rating model, wherein the rating model utilizes a machine learning model, the machine learning model configured to output a rating based on a degree of similarity evaluated between the obtained textual description and a set of selected textual descriptions;
generating, based on the rating generated based on the obtained textual description, a suggested modification of the obtained textual description that, when applied to the obtained textual description, would have a rating different from the rating generated based on the obtained textual description.
2 . The computer-implemented method of claim 1 , further comprising outputting an indication of the suggested modification, the outputting including:
displaying the obtained textual description via a user interface; and
displaying a control, at a selected location within the displayed obtained textual description, that is operable to change text related to the identified feature type at the selected location.
3 . The computer-implemented method of claim 1 , wherein generating the suggested modification comprises:
identifying a portion of the obtained textual description that, if replaced by a modified portion of text, would improve the rating of the obtained textual description;
wherein the suggested modification includes the modified portion of text.
4 . The computer-implemented method of claim 3 , further comprising:
displaying the obtained textual description via a user interface, wherein the identified portion of the obtained textual description is emphasized in the displayed obtained textual description; and
displaying a control that is operable to replace the identified portion of the obtained textual description with the modified portion of text.
5 . The computer-implemented method of claim 1 , further comprising:
generating for respective selected textual descriptions in the set of selected textual descriptions, using the rating model, a uniqueness rating indicating a degree of uniqueness of the respective selected textual description relative to other selected textual descriptions in the set of selected textual description; and
determining a range of the uniqueness ratings of the set of selected textual descriptions;
wherein scoring the obtained textual description further comprises outputting an assessment of the rating of the obtained textual description relative to the range of the uniqueness ratings of the set of selected textual descriptions.
6 . The computer-implemented method of claim 5 , wherein a higher rating indicates the obtained textual description is more unique relative to the set of selected textual descriptions and, if a size of the range of the uniqueness ratings of the set of selected textual descriptions is greater than a threshold size, the suggested modification, when applied to the obtained textual description, would cause the rating of the obtained textual description to increase.
7 . The computer-implemented method of claim 5 , wherein a higher rating indicates the obtained textual description is more similar to the set of selected textual descriptions and, if a size of the range of the uniqueness ratings of the set of selected textual descriptions is less than a threshold size, the suggested modification, when applied to the obtained textual description, would cause the rating of the obtained textual description to increase.
8 . The computer-implemented method of claim 1 , wherein the obtained textual description describes a particular object in a particular category, and wherein the set of selected textual descriptions comprises selected textual descriptions that are related to corresponding entities in the particular category.
9 . The computer-implemented method of claim 1 , wherein the obtained textual description describes a particular object that is associated with a structured body of data, and wherein the method further comprises:
determining a degree of similarity between the structured body of data associated with the specified object and other structured bodies of data corresponding to other entities; and
selecting one or more of the other entities for which the structured body of data associated with the selected entities is within a threshold similarity to the structured body of data associated with the specified object;
wherein the set of selected textual descriptions comprises textual descriptions corresponding to the selected entities.
10 . The computer-implemented method of claim 1 , further comprising:
measuring performance of two or more textual descriptions; and
selecting, as the set of selected textual descriptions, one or more of the two or more textual descriptions based on the measured performance.
11 . The computer-implemented method of claim 1 , further comprising outputting an indication of the suggested modification, comprising:
automatically regenerating a portion of the obtained textual description; and
displaying, via a user interface, a modified version of the obtained textual description including the regenerated portion.
12 . The computer-implemented method of claim 1 , wherein the rating model further utilizes a large language model (LLM).
13 . The computer-implemented method of claim 12 , wherein the obtained textual description is generated at least in part by the LLM.
14 . The computer-implemented method of claim 1 , wherein each of the set of selected textual descriptions include respective bodies of unstructured text.
15 . The computer-implemented method of claim 1 , wherein the textual description includes a description of a first feature of an object, and wherein the suggested modification comprises a suggestion to add a description of a second feature of the object.
16 . A non-transitory computer readable storage medium storing executable instructions, execution of which by a processor causing the processor to:
obtain, using a large language model, a textual description that includes a body of unstructured text;
generate a rating based on the obtained textual description using a rating model, wherein the rating model utilizes a machine learning model, the machine learning model configured to output a rating based on a degree of similarity evaluated between the obtained textual description and a set of selected textual descriptions;
generate, based on the rating generated based on the obtained textual description, a suggested modification of the obtained textual description that, when applied to the obtained textual description, would have a rating different from the rating generated based on the obtained textual description.
17 . The non-transitory computer readable storage medium of claim 16 , execution of which by the processor further causing the processor to output an indication of the suggested modification, the outputting including:
displaying the obtained textual description via a user interface; and
displaying a control, at a selected location within the displayed obtained textual description, that is operable to change text related to the identified feature type at the selected location.
18 . The non-transitory computer readable storage medium of claim 16 , wherein generating the suggested modification comprises:
identifying a portion of the obtained textual description that, if replaced by a modified portion of text, would improve the rating of the obtained textual description;
wherein the suggested modification includes the modified portion of text.
19 . The non-transitory computer readable storage medium of claim 16 , wherein the rating model further utilizes a large language model (LLM).
20 . A system comprising:
at least one hardware processor; and
at least one non-transitory memory storing instructions, which, when executed by the at least one hardware processor, cause the system to:
obtain, using a large language model, a textual description that includes a body of unstructured text;
generate a rating based on the obtained textual description using a rating model, wherein the rating model utilizes a machine learning model, the machine learning model configured to output a rating based on a degree of similarity evaluated between the obtained textual description and a set of selected textual descriptions;
generate, based on the rating generated based on the obtained textual description, a suggested modification of the obtained textual description that, when applied to the obtained textual description, would have a rating different from the rating generated based on the obtained textual description.