Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents

TL;DR

This paper investigates how large language models express personality differently across various conversational contexts, revealing that their behavior adapts flexibly to social and emotional cues, similar to human personality expression.

Contribution

It demonstrates that LLMs exhibit context-sensitive personality expression, influenced by social and affective demands, advancing understanding of their behavioral variability.

Findings

Context influences linguistic and emotional expression in LLMs.

Personality traits are expressed differently depending on interaction context.

LLMs adapt personality expression based on social and emotional cues.

Abstract

Large Language Models (LLMs) can be conditioned with explicit personality prompts, yet their behavioral realization often varies depending on context. This study examines how identical personality prompts lead to distinct linguistic, behavioral, and emotional outcomes across four conversational settings: ice-breaking, negotiation, group decision, and empathy tasks. Results show that contextual cues systematically influence both personality expression and emotional tone, suggesting that the same traits are expressed differently depending on social and affective demands. This raises an important question for LLM-based dialogue agents: whether such variations reflect inconsistency or context-sensitive adaptation akin to human behavior. Viewed through the lens of Whole Trait Theory, these findings highlight that LLMs exhibit context-sensitive rather than fixed personality expression, adapting flexibly to social interaction goals and affective conditions.