Can LLM Agents Maintain a Persona in Discourse?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhandari, Pranav, Fay, Nicolas, Wise, Michael, Datta, Amitava, Meek, Stephanie, Naseem, Usman, Nasim, Mehwish
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929718217932800
author Bhandari, Pranav
Fay, Nicolas
Wise, Michael
Datta, Amitava
Meek, Stephanie
Naseem, Usman
Nasim, Mehwish
author_facet Bhandari, Pranav
Fay, Nicolas
Wise, Michael
Datta, Amitava
Meek, Stephanie
Naseem, Usman
Nasim, Mehwish
contents Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more. However, LLMs are often subjected to context-shifting behaviour, resulting in a lack of consistent and interpretable personality-aligned interactions. Adherence to psychological traits lacks comprehensive analysis, especially in the case of dyadic (pairwise) conversations. We examine this challenge from two viewpoints, initially using two conversation agents to generate a discourse on a certain topic with an assigned personality from the OCEAN framework (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) as High/Low for each trait. This is followed by using multiple judge agents to infer the original traits assigned to explore prediction consistency, inter-model agreement, and alignment with the assigned personality. Our findings indicate that while LLMs can be guided toward personality-driven dialogue, their ability to maintain personality traits varies significantly depending on the combination of models and discourse settings. These inconsistencies emphasise the challenges in achieving stable and interpretable personality-aligned interactions in LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11843
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLM Agents Maintain a Persona in Discourse?
Bhandari, Pranav
Fay, Nicolas
Wise, Michael
Datta, Amitava
Meek, Stephanie
Naseem, Usman
Nasim, Mehwish
Computation and Language
Artificial Intelligence
Social and Information Networks
I.2.7
Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more. However, LLMs are often subjected to context-shifting behaviour, resulting in a lack of consistent and interpretable personality-aligned interactions. Adherence to psychological traits lacks comprehensive analysis, especially in the case of dyadic (pairwise) conversations. We examine this challenge from two viewpoints, initially using two conversation agents to generate a discourse on a certain topic with an assigned personality from the OCEAN framework (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) as High/Low for each trait. This is followed by using multiple judge agents to infer the original traits assigned to explore prediction consistency, inter-model agreement, and alignment with the assigned personality. Our findings indicate that while LLMs can be guided toward personality-driven dialogue, their ability to maintain personality traits varies significantly depending on the combination of models and discourse settings. These inconsistencies emphasise the challenges in achieving stable and interpretable personality-aligned interactions in LLMs.
title Can LLM Agents Maintain a Persona in Discourse?
topic Computation and Language
Artificial Intelligence
Social and Information Networks
I.2.7
url https://arxiv.org/abs/2502.11843