Paper: arXiv 2411.05801

Authors: Harris Borman, Anna Leontjeva, Luiz Pizzato, Max Kun Jiang, Dan Jermyn

Abstract

Large Language Models (LLMs) have demonstrated the ability to adopt a personality and behave in a human-like manner. There is a large body of research that investigates the behavioural impacts of personality in less obvious areas such as investment attitudes or creative decision making. In this study, we investigated whether an LLM persona with a specific Big Five personality profile would perform an investment task similarly to a human with the same personality traits. We used a simulated investment task to determine if these results could be generalised into actual behaviours. In this simulated environment, our results show these personas produced meaningful behavioural differences in all assessed categories, with these behaviours generally being consistent with expectations derived from human research. We found that LLMs are able to generalise traits into expected behaviours in three areas: learning style, impulsivity and risk appetite while environmental attitudes could not be accurately represented. In addition, we showed that LLMs produce behaviour that is more reflective of human behaviour in a simulation environment compared to a survey environment.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper applies established statistical methods (OLS regression) and standard personality models (Big Five) with moderate complexity, but its primary contribution is a simulation-based empirical study comparing LLM personas to human behavior in an investment task, involving specific data collection and implementation steps.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Do LLM Personas mirror human investment behavior<br>based on Five-Factor Model traits?"] --> B

  subgraph B ["Methodology & Data"]
      direction LR
      B1["Big Five<br>Personality Profiles"] --> B2["Investment Task<br>Simulated Environment"]
      B3["Human Baseline<br>Survey Data"] --> B2
  end

  B --> C["Computational Process<br>LLM Simulation & Comparative Analysis"]

  C --> D{"Outcome 1: Behavioral Consistency"}
  C --> E{"Outcome 2: Domain Generalization"}
  C --> F{"Outcome 3: Context Sensitivity"}

  D --> D1["LLM personas exhibited meaningful<br>behavioral differences across categories"]
  E --> E1["Accurate representation in:<br>Learning Style, Impulsivity, Risk Appetite"]
  E --> E2["Failed representation in:<br>Environmental Attitudes"]
  F --> F1["Simulation behavior more reflective<br>of human behavior vs. Survey"]

  style A fill:#e1f5fe
  style B fill:#fff3e0
  style C fill:#f3e5f5
  style D fill:#e8f5e8
  style E fill:#e8f5e8
  style F fill:#e8f5e8

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper investigates whether LLM-powered personas can reliably interpret the five-factor personality model and map traits into investment‑related behaviours consistent with human research.

Source sentence
In this study, we investigated whether an LLM persona with a specific Big Five personality profile would perform an investment task similarly to a human with the same personality traits. This study aims to address this limitation by investigating if LLM-powered personas 1 can reliably interpret a human personality model (specifically the five-factor model) and map personality traits into specific behaviours that are

Assumes 2

  • Personas are given only personality trait information and no additional demographic or contextual data. model
    Source sentence
    Prompts were constructed to have only information about the persona’s personality traits with no extra information provided (See Appendix A for prompt).
  • Ordinary least squares regression is appropriate for identifying correlations between personality traits and behaviours. statistical
    Source sentence
    For both tests we used an ordinary least squares (OLS) regression to identify correlations between personality traits and each desired behaviour.

Data

  • Behavioural survey synthetic proprietary
    Source sentence
    2.2 Behavioural survey To measure if personas can correctly associate personality with behaviour, we constructed a simple behavioural survey.
  • Investment simulation synthetic proprietary
    Source sentence
    2.3 Investment simulation To determine if LLMs were interpreting their personality traits to produce different behaviours, as opposed to simply learning the expected answer to each question during training, we constructed a simple investment task.

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • LLM personas accurately reflect human personality in learning style, impulsive decision making and risk appetite, but cannot reliably represent environmental attitudes. performance
    Source sentence
    We found that LLMs can accurately reflect a human personality in the areas of learning style, impulsive decision making and risk appetite while environmental attitudes could not be reliably interpreted.
  • Personas produce more accurate human‑like behaviour in a simulated investment task than when answering survey questions. performance
    Source sentence
    We observed that in all these cases LLM personas produced a more accurate simulation of human behaviour when performing a simulated task compared to answering questions in a survey.
  • During training LLMs learn associations between personality traits and behaviours, enabling generalisation to novel simulated tasks. theoretical
    Source sentence
    The observed behaviour suggests that during the training process the LLM has learnt to make associations between personality traits and behaviours themselves allowing them to produce an accurate representation of human behaviour in these areas when operating in a simulated environment.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 8 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (30)

  1. Generative Agents: Interactive Simulacra of Human Behavior (2023) — link
  2. Multi-Agent Software Development through Cross-Team Collaboration (2024) — link
  3. PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits (2024) — link
  4. The use of ChatGPT for personality research: Administering questionnaires using generated personas (2024) — link
  5. Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics (2024) — link
  6. THE EFFECT OF BIG FIVE PERSONALITY IN CREATIVE DECISION MAKING (2009)
  7. The role of personality traits in green decision-making (2017) — link
  8. IMPACT OF PERSONALITY TRAITS OF PROJECT MANAGER ON PROJECT SUCCESS (2018) — link
and 22 more
  1. LLMs with Personalities in Multi-issue Negotiation Games (2024) — link
  2. Personality, decision-making styles and investments (2019) — link
  3. Personality and Health Care Decision-Making Style (2007) — link
  4. The Cambridge Handbook of Personality Psychology (2020)
  5. Investment management and personality type (2008)
  6. Personality Traits and Risky Decision-Making in a Controlled Experimental Task: An Exploratory Study (2001) — link
  7. Who Does Well in Life? Conscientious Adults Excel in Both Objective and Subjective Success (2012) — link
  8. Comparing Two Alternative Measures of General Personality in the Assessment of Psychopathy: A Test of the NEO PI-R and the MPQ (2009) — link
  9. The Effects of Personality Traits and Website Quality on Online Impulse Buying (2015) — link
  10. The Mediating Role of Affect in the Relationship between the Big Five Factor Personality and Risk Aversion: A Structural Model (2018) — link
  11. Personality and problem-solving: The nature of individual differences in planning, scanning and verification (1985) — link
  12. LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models (2024) — link
  13. Better Zero-Shot Reasoning with Role-Play Prompting (2024) — link
  14. The relationship between Personality Traits, Learning Styles and Academic Performance of E-Learners ( 2018 ) — link
  15. The Five-Factor Model of Personality and Its Relevance to Personality Disorders (1992) — link
  16. Towards Understanding Assessments of the Big Five: Multitrait-Multimethod Analyses of Convergent and Discriminant Validity Across Measurement Occasion and Type of Observer (2004) — link
  17. FIVE REASONS WHY THE “BIG FIVE” ARTICLE HAS BEEN FREQUENTLY CITED (1998) — link
  18. Critical Review on Affect of Personality on Learning Styles. (2012) — link
  19. Relationship among Personality Traits, Extraversion & Agreeableness with Students Preferred Learning Styles at Higher Education (2020) — link
  20. The Five Factor Model and impulsivity: using a structural model of personality to understand impulsivity (2001) — link
  21. The Effects of Personality Traits and Website Quality on Online Impulse Buying (2015) — link
  22. Personality and Domain-Specific Risk Taking (2005) — link

0 of 30 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.