Personalized responses to chatbot prompt based on embedding spaces between user and society

A system comprising:

• one or more processors;
• and
• memory storing instructions that, when executed by the one or more processors, cause the system to:
• receive, from a user device associated with a user, a prompt;
• train, based on historical chat information from a plurality of users representative of acceptable views of society, a first machine learning model to determine general Overton windows, wherein the historical chat information comprising a plurality of prompt-response pairs from the plurality of users;
• determine, using the first machine learning model and based on the prompt, a general Overton window associated with the prompt;
• determine, based on the prompt and using the first machine learning model, a user-specific Overton window associated with the prompt;
• generate, using the first machine learning model and based on the user-specific Overton window, a plurality of candidate responses;
• input the prompt and the plurality of candidate responses to a second machine learning model;
• receive, as output from the second machine learning model, a polarization score for each of the plurality of candidate responses;
• re-train, based on the polarization score generated by the second machine learning model, the first machine learning model;
• select, from the plurality of candidate responses and based on the polarization score associated with each of the plurality of candidate responses, a recommended response that minimizes a distance between the user-specific Overton window and the general Overton window;
• and
• cause display of the recommended response to the prompt on the user device.

One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause a computing device to:

• receive from a user device of a user, a prompt;
• train, based on historical chat information that represents one or more acceptable views of society, a first machine learning model to determine general Overton windows, wherein the historical chat information comprises a plurality of prompt-response pairs from a plurality of users;
• determine, based on the prompt and using the first machine learning model, a general Overton window associated with the prompt;
• determine, based on the prompt and using the first machine learning model, a user-specific Overton window associated with the prompt;
• generate, using the first machine learning model and based on the user-specific Overton window, a plurality of candidate responses;
• input the prompt and the plurality of candidate responses to a second machine learning model;
• receive, as output from the second machine learning model, a polarization score for each of the plurality of candidate responses;
• determine that the general Overton window and the user-specific Overton window do not overlap with each other;
• select, based on the polarization score and from the plurality of candidate responses falling within the user-specific Overton window that minimizes a distance between the user-specific Overton window and the general Overton window, a recommended response;
• and
• cause display of the recommended response to the prompt on the user device.