Personality Traits in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Serapio-García, Greg, Safdari, Mustafa, Crepy, Clément, Sun, Luning, Fitz, Stephen, Romero, Peter, Abdulhai, Marwa, Faust, Aleksandra, Matarić, Maja
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915191931797504
author Serapio-García, Greg
Safdari, Mustafa
Crepy, Clément
Sun, Luning
Fitz, Stephen
Romero, Peter
Abdulhai, Marwa
Faust, Aleksandra
Matarić, Maja
author_facet Serapio-García, Greg
Safdari, Mustafa
Crepy, Clément
Sun, Luning
Fitz, Stephen
Romero, Peter
Abdulhai, Marwa
Faust, Aleksandra
Matarić, Maja
contents The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant human-like text. As LLMs increasingly powerconversational agents used by the general public world-wide, the synthetic personality traits embedded in these models, by virtue of training on large amounts of human data, is becoming increasingly important. Since personality is a key factor determining the effectiveness of communication, we present a novel and comprehensive psychometrically valid and reliable methodology for administering and validating personality tests on widely-used LLMs, as well as for shaping personality in the generated text of such LLMs. Applying this method to 18 LLMs, we found: 1) personality measurements in the outputs of some LLMs under specific prompting configurations are reliable and valid; 2) evidence of reliability and validity of synthetic LLM personality is stronger for larger and instruction fine-tuned models; and 3) personality in LLM outputs can be shaped along desired dimensions to mimic specific human personality profiles. We discuss the application and ethical implications of the measurement and shaping method, in particular regarding responsible AI.
format Preprint
id arxiv_https___arxiv_org_abs_2307_00184
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Personality Traits in Large Language Models
Serapio-García, Greg
Safdari, Mustafa
Crepy, Clément
Sun, Luning
Fitz, Stephen
Romero, Peter
Abdulhai, Marwa
Faust, Aleksandra
Matarić, Maja
Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
68T35
I.2.7
The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant human-like text. As LLMs increasingly powerconversational agents used by the general public world-wide, the synthetic personality traits embedded in these models, by virtue of training on large amounts of human data, is becoming increasingly important. Since personality is a key factor determining the effectiveness of communication, we present a novel and comprehensive psychometrically valid and reliable methodology for administering and validating personality tests on widely-used LLMs, as well as for shaping personality in the generated text of such LLMs. Applying this method to 18 LLMs, we found: 1) personality measurements in the outputs of some LLMs under specific prompting configurations are reliable and valid; 2) evidence of reliability and validity of synthetic LLM personality is stronger for larger and instruction fine-tuned models; and 3) personality in LLM outputs can be shaped along desired dimensions to mimic specific human personality profiles. We discuss the application and ethical implications of the measurement and shaping method, in particular regarding responsible AI.
title Personality Traits in Large Language Models
topic Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
68T35
I.2.7
url https://arxiv.org/abs/2307.00184