# Personality Vector: Modulating Personality of Large Language Models by Model Merging

arXiv: https://arxiv.org/abs/2509.19727 · HTML: https://mlsanity.com/paper/2509.19727/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Dataless Knowledge Fusion by Merging Weights of Language Models](https://mlsanity.com/paper/2212.09849/) (2022)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [tinyBenchmarks: evaluating LLMs with fewer examples](https://mlsanity.com/paper/2402.14992/) (2024)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Evolutionary Optimization of Model Merging Recipes](https://mlsanity.com/paper/2403.13187/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models](https://mlsanity.com/paper/2208.03306/) (2022)
- [Patching open-vocabulary models by interpolating weights](https://mlsanity.com/paper/2208.05592/) (2022)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [EMR-Merging: Tuning-Free High-Performance Model Merging](https://mlsanity.com/paper/2405.17461/) (2024)
- [Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages](https://mlsanity.com/paper/2310.04799/) (2023)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [BitDelta: Your Fine-Tune May Only Be Worth One Bit](https://mlsanity.com/paper/2402.10193/) (2024)
- [ControlLM: Crafting Diverse Personalities for Language Models](https://mlsanity.com/paper/2402.10151/) (2024)

## Built on by (most cited first, 17 of 17)

- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation](https://mlsanity.com/paper/2510.10157/) (2025)
- [Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations](https://mlsanity.com/paper/2601.09833/) (2026)
- [Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs](https://mlsanity.com/paper/2511.03738/) (2025)
- [Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models](https://mlsanity.com/paper/2602.15847/) (2026)
- [Persona Cartography: Charting Language Model Personality Traits in Weight Space](https://mlsanity.com/paper/2607.07916/) (2026)
- [Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer](https://mlsanity.com/paper/2608.20442/) (2026)
- [One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles](https://mlsanity.com/paper/2608.27338/) (2026)
- [Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models](https://mlsanity.com/paper/2603.15405/) (2026)
- [Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness](https://mlsanity.com/paper/2606.10413/) (2026)
- [Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models](https://mlsanity.com/paper/2606.11074/) (2026)
- [Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging](https://mlsanity.com/paper/2607.08540/) (2026)
- [What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors](https://mlsanity.com/paper/2607.13162/) (2026)
- [From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs](https://mlsanity.com/paper/2607.26853/) (2026)
- [Training-Free Task Vectors for LLM Behavioral Control](https://mlsanity.com/paper/2609.09054/) (2026)
- [Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs](https://mlsanity.com/paper/2609.15654/) (2026)
- [PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations](https://mlsanity.com/paper/2609.34571/) (2026)

## Abstract (arXiv)

Driven by the demand for personalized AI systems, there is growing interest in aligning the behavior of large language models (LLMs) with human traits such as personality. Previous attempts to induce personality in LLMs have shown promising results, but they struggle to capture the continuous and multidimensional nature of human traits. In this work, we propose a novel method for personality modulation in LLMs via model merging. Specifically, we construct personality vectors by subtracting the weights of a pre-trained model from those of the fine-tuned model on a given personality trait. By merging personality vectors, we enable LLMs to exhibit desired personality traits without additional training. Extensive experiments show that personality vectors enable continuous control over trait intensity and support the composition of multiple traits. Furthermore, personality vectors transfer across diverse downstream models, suggesting that they encode generalizable representations of personality. Our code is available at here.