Absorbing and Mirroring Personalities of Users of Large Language Models

Absorbing and Mirroring Personalities of Users of Large Language Models

πŸ”— Contact Information

Department of Psychology
777 Glades Road
Boca Raton, FL 33431-0991
S.E. Wimberly Library
Sandbox
[email protected]

πŸ”— Project Leader

Richard Matic

πŸ”— Collaborators

Jasmine Makkar, Avery Lawrence

πŸ”— Supervisors

πŸ”— Project Description

This Ph.D. dissertation is intended to test a novel way to absorb the personality of users of large language models (LLM’s). Dramatis persona is a construct in creative writing which emobodies a character’s personality in just a few sentences and can carry that character through dramatic arcs in multiple created or LLM-generated stories. This project will attempt to extract a dramatis persona of a user based on the user’s dialog and personal descriptions. That dramatis persona will then be used to synthesize a matching (or mirrored) personality of the LLM. The method will be compared to other approaches to personality mirroring, including Big Five.

πŸ”— Pictures (If Applicable)

πŸ”— SKIP ALL OF THESE FOR NOW


πŸ”— Demos (Skip)

πŸ”— Code / Git Repo (Skip)

πŸ”— Publications / Presentations (Skip)

πŸ”— Funding (Skip)