Implicit Personality Representations in Humans and LLMs

• URL: http://arxiv.org/abs/2609.12704v1
• Date: Fri, 11 Sep 2026 10:54:42 GMT
• Title: Implicit Personality Representations in Humans and LLMs
• Abstract summary: We build a human implicit-personality matrix over hundreds of traits.<n>From contrastive model activations, we build a matching matrix over the same traits.<n>The two relational structures align strongly (Mantel r = 0.77), and the agreement holds trait by trait as well as in aggregate.
• Score: 20.689781190240428
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A century of psychology has found that the trait words people use to describe one another vary, but the relational structure among those traits, which ones go together and which oppose, is strikingly consistent across raters and cultures. We test whether the LLM (Qwen 2.5-7B-Instruct) reproduces this structure in its internal trait representations. From millions of crowd-sourced personality ratings of fictional characters, we build a human implicit-personality matrix over hundreds of traits; from contrastive model activations, we build a matching matrix over the same traits. The two relational structures align strongly (Mantel r = 0.77), and the agreement holds trait by trait as well as in aggregate. Two dominant axes of the model's trait representations recover the social and intellectual dimensions long known to organize human personality impressions, social warmth and intellectual competence. On held-out dialogue, projecting model activations onto these directions yields personality profiles that agree with human ratings. This work establishes a framework that enables comprehensive, human-grounded comparison between internal model trait geometry and the shared structure of human personality impressions.

Related papers

• HEART-Bench: Do LLM Agents Exhibit Human-like Psychology? [25.237337617299946]
  This paper introduces a novel benchmark to assess whether LLM agents can simulate coherent, human-like psychology.<n>Our benchmark constructs 11 diverse human characters grounded in Big Five personality traits, with each profile deeply integrated with 1,000 structured autobiographical-style episodic memories.<n>By subjecting agents to varying scenarios, the benchmark evaluates whether they can consolidate their innate personality traits and autobiographical memories to make behavioral decisions consistent with their specific psychological profiles.
  arXiv  Detail & Related papers  (2026-05-28T15:08:03Z)
• HUMANLLM: Benchmarking and Reinforcing LLM Anthropomorphism via Human Cognitive Patterns [59.17423586203706]
  We present HUMANLLM, a framework treating psychological patterns as interacting causal forces.<n>We construct 244 patterns from 12,000 academic papers and synthesize 11,359 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.<n>Our dual-level checklists evaluate both individual pattern fidelity and emergent multi-pattern dynamics, achieving strong human alignment.
  arXiv  Detail & Related papers  (2026-01-15T08:56:53Z)
• Fame Fades, Nature Remains: Disentangling the Character Identity of Role-Playing Agents [13.029517493304505]
  We propose a multidimensional construct that disentangles a character into two distinct layers: textbf(1) Parametric Identity, referring to character-specific knowledge encoded from the LLM's pre-training, and textbf(2) Attributive Identity, capturing fine-grained behavioral properties such as personality traits and moral values.<n>Our findings pinpoint negative social natures as the primary bottleneck in RPA fidelity, guiding future character construction and evaluation.
  arXiv  Detail & Related papers  (2026-01-08T08:33:40Z)
• TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation [55.55404595177229]
  Large Language Models (LLMs) are exhibiting emergent human-like abilities.<n>TwinVoice is a benchmark for assessing persona simulation across diverse real-world contexts.
  arXiv  Detail & Related papers  (2025-10-29T14:00:42Z)
• The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs [60.15472325639723]
  Personality traits have long been studied as predictors of human behavior.<n>Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems.
  arXiv  Detail & Related papers  (2025-09-03T21:27:10Z)
• Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires [3.6001840369062386]
  This work applies psychological tools to Large Language Models in diverse scenarios to generate personality profiles.<n>Our findings reveal that LLMs exhibit unique traits, varying characteristics, and distinct personality profiles even within the same family of models.
  arXiv  Detail & Related papers  (2025-02-07T16:12:52Z)
• Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues [63.936654900356004]
  Personality recognition aims to identify the personality traits implied in user data such as dialogues and social media posts. We propose a novel task named Explainable Personality Recognition, aiming to reveal the reasoning process as supporting evidence of the personality trait.
  arXiv  Detail & Related papers  (2024-09-29T14:41:43Z)
• Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions [2.6080756513915824]
  Personality, a fundamental aspect of human cognition, contains a range of traits that influence behaviors, thoughts, and emotions. This paper explores the capabilities of large language models (LLMs) in reconstructing these complex cognitive attributes based only on simple descriptions containing socio-demographic and personality type information.
  arXiv  Detail & Related papers  (2024-06-18T02:32:57Z)
• PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection [50.66968526809069]
  We propose a novel personality detection method, called PsyCoT, which mimics the way individuals complete psychological questionnaires in a multi-turn dialogue manner. Our experiments demonstrate that PsyCoT significantly improves the performance and robustness of GPT-3.5 in personality detection.
  arXiv  Detail & Related papers  (2023-10-31T08:23:33Z)
• Editing Personality for Large Language Models [73.59001811199823]
  This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs) We construct PersonalityEdit, a new benchmark dataset to address this task.
  arXiv  Detail & Related papers  (2023-10-03T16:02:36Z)
• Identifying and Manipulating the Personality Traits of Language Models [9.213700601337383]
  We investigate whether perceived personality in language models is exhibited consistently in their language generation. We show that language models such as BERT and GPT2 can consistently identify and reflect personality markers in different contexts. This behavior illustrates an ability to be manipulated in a highly predictable way, and frames them as tools for identifying personality traits and controlling personas in applications such as dialog systems.
  arXiv  Detail & Related papers  (2022-12-20T14:24:11Z)
• Evaluating and Inducing Personality in Pre-trained Language Models [78.19379997967191]
  We draw inspiration from psychometric studies by leveraging human personality theory as a tool for studying machine behaviors. To answer these questions, we introduce the Machine Personality Inventory (MPI) tool for studying machine behaviors. MPI follows standardized personality tests, built upon the Big Five Personality Factors (Big Five) theory and personality assessment inventories. We devise a Personality Prompting (P2) method to induce LLMs with specific personalities in a controllable way.
  arXiv  Detail & Related papers  (2022-05-20T07:32:57Z)
• My tweets bring all the traits to the yard: Predicting personality and relational traits in Online Social Networks [4.095574580512599]
  This study aims to provide a prediction model for a holistic personality profiling in Online Social Networks (OSNs) We first designed a feature engineering methodology that extracts a wide range of features from OSN accounts of users. Then, we designed a machine learning model that predicts scores for the psychological traits of the users based on the extracted features.
  arXiv  Detail & Related papers  (2020-09-22T20:30:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.