# Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptors

arXiv: https://arxiv.org/abs/2409.09905 · HTML: https://mlsanity.com/paper/2409.09905/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Virtual Personas for Language Models via an Anthology of Backstories](https://mlsanity.com/paper/2407.06576/) (2024)
- [Self-Assessment Tests are Unreliable Measures of LLM Personality](https://mlsanity.com/paper/2309.08163/) (2023)
- [LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models](https://mlsanity.com/paper/2402.02896/) (2024)
- [Large Language Models Can Infer Psychological Dispositions of Social Media Users](https://mlsanity.com/paper/2309.08631/) (2023)
- [Challenging the Validity of Personality Tests for Large Language Models](https://mlsanity.com/paper/2311.05297/) (2023)
- [Personality Trait Detection Using Bagged SVM over BERT Word Embedding Ensembles](https://mlsanity.com/paper/2010.01309/) (2020)
- [Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation](https://mlsanity.com/paper/2404.02589/) (2024)

## Built on by (most cited first, 6 of 6)

- [Mechanistic Interpretability of Emotion Inference in Large Language Models](https://mlsanity.com/paper/2502.05489/) (2025)
- [From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers](https://mlsanity.com/paper/2511.03235/) (2025)
- [Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humans](https://mlsanity.com/paper/2601.16355/) (2026)
- [Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models](https://mlsanity.com/paper/2509.16332/) (2025)
- [Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control](https://mlsanity.com/paper/2608.10703/) (2026)
- [Implicit Personality Representations in Humans and LLMs](https://mlsanity.com/paper/2609.12704/) (2026)

## Abstract (arXiv)

Assessing personality traits using large language models (LLMs) has emerged as an interesting and challenging area of research. While previous methods employ explicit questionnaires, often derived from the Big Five model of personality, we hypothesize that LLMs implicitly encode notions of personality when modeling next-token responses. To demonstrate this, we introduce a novel approach that uncovers latent personality dimensions in LLMs by applying singular value de-composition (SVD) to the log-probabilities of trait-descriptive adjectives. Our experiments show that LLMs "rediscover" core personality traits such as extraversion, agreeableness, conscientiousness, neuroticism, and openness without relying on direct questionnaire inputs, with the top-5 factors corresponding to Big Five traits explaining 74.3% of the variance in the latent space. Moreover, we can use the derived principal components to assess personality along the Big Five dimensions, and achieve improvements in average personality prediction accuracy of up to 5% over fine-tuned models, and up to 21% over direct LLM-based scoring techniques.