Persona Cartography: Charting Language Model Personality Traits in Weight Space

• URL: http://arxiv.org/abs/2607.07916v1
• Date: Wed, 08 Jul 2026 21:00:44 GMT
• Title: Persona Cartography: Charting Language Model Personality Traits in Weight Space
• Abstract summary: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety.<n>We treat personas as positions in a space of behavioural traits, using the OCEAN framework to describe model personas.<n>We train low-rank adapters to amplify or suppress individual traits, and evaluate their effects using an LLM-judge calibrated against a human-validated panel.
• Score: 2.3772203606681415
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them. Our central insight is to treat personas as positions in a space of behavioural traits, using the OCEAN framework to describe model personas in terms of Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. We train low-rank adapters to amplify or suppress individual traits, and evaluate their effects using an LLM-judge calibrated against a human-validated panel, trait-specific multiple-choice benchmarks, and standard capability evaluations. Across six models from three families (4B-32B), we find that each adapter moves its target trait largely monotonically with scale, combines approximately additively with other adapters to construct mixed personas, and preserves performance on capability benchmarks at moderate scales. We further show that the induced trait axes affect safety-relevant behaviour in downstream evaluations: for example, moving along neuroticism and agreeableness axes affects frustration and sycophancy respectively. We also introduce an unsupervised psychometric pipeline that recovers four interpretable behavioural factors (tone, initiative, didacticism, epistemic caution) from model rollouts. Persona control can then be considered in terms of learning, scaling, and composing traits in weight space, providing a bridge between personality measurement, model editing, and safety.

Related papers

• Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact [1.3277433989254843]
  Psychological instruments designed for humans are increasingly used to assign large language models (LLMs) stable psychological profiles.<n>Using a formal psychometric framework, we show that these profiles are largely a measurement artifact.
  arXiv  Detail & Related papers  (2026-06-18T13:18:37Z)
• PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra [84.59328460968872]
  Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning.<n>We introduce PERSONA, a training-free framework that achieves fine-tuning level performance through direct manipulation of personality vectors.<n>On PersonalityBench, our approach achieves a mean score of 9.60, nearly matching the supervised fine-tuning upper bound of 9.61 without any gradient updates.
  arXiv  Detail & Related papers  (2026-02-17T15:47:58Z)
• Enhancing Personality Recognition by Comparing the Predictive Power of Traits, Facets, and Nuances [37.83859643892549]
  Personality recognition models aim to infer personality traits from different sources of behavioral data.<n>We trained a transformer-based model including cross-modal (audiovisual) and cross-subject (dyad-aware) attention mechanisms.<n>Results show that nuance-level models consistently outperform facet and trait-level models, reducing mean squared error by up to 74% across interaction scenarios.
  arXiv  Detail & Related papers  (2026-02-05T13:35:04Z)
• 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)
• Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation [16.76995815742803]
  We propose an atomic-level evaluation framework that quantifies persona fidelity at a finer granularity.<n>Our three key metrics measure the degree of persona alignment and consistency within and across generations.<n>By analyzing persona fidelity across diverse tasks and personality types, we reveal how task structure and persona desirability influence model adaptability.
  arXiv  Detail & Related papers  (2025-06-24T06:33:10Z)
• 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)
• ControlLM: Crafting Diverse Personalities for Language Models [32.411304295746746]
  We introduce ControlLM, which leverages differential activation patterns, derived from contrasting behavioral prompts in the model's latent space, to influence the model's personality traits at inference. First, we demonstrate ControlLM's capacity to elicit diverse persona behaviors without any training, while precision control allows personality traits to closely match average human values. We showcase improved reasoning and question answering through selective amplification of beneficial attributes like conscientiousness and friendliness.
  arXiv  Detail & Related papers  (2024-02-15T17:58:29Z)
• Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach [61.04606493712002]
  Susceptibility to misinformation describes the degree of belief in unverifiable claims that is not observable. Existing susceptibility studies heavily rely on self-reported beliefs. We propose a computational approach to model users' latent susceptibility levels.
  arXiv  Detail & Related papers  (2023-11-16T07:22:56Z)
• 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)
• AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model [69.12623428463573]
  AlignDiff is a novel framework to quantify human preferences, covering abstractness, and guide diffusion planning. It can accurately match user-customized behaviors and efficiently switch from one to another. We demonstrate its superior performance on preference matching, switching, and covering compared to other baselines.
  arXiv  Detail & Related papers  (2023-10-03T13:53:08Z)
• Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards Individualized and Explainable Robotic Support in Everyday Activities [80.37857025201036]
  Key challenge for robotic systems is to figure out the behavior of another agent. Processing correct inferences is especially challenging when (confounding) factors are not controlled experimentally. We propose equipping robots with the necessary tools to conduct observational studies on people.
  arXiv  Detail & Related papers  (2022-01-27T22:15:56Z)

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.