# Your Language Model Secretly Contains Personality Subnetworks

arXiv: https://arxiv.org/abs/2602.07164 · HTML: https://mlsanity.com/paper/2602.07164/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 36 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 30 of 33)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs](https://mlsanity.com/paper/2502.09597/) (2025)
- [Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization](https://mlsanity.com/paper/2310.03708/) (2023)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [HYDRA: Model Factorization Framework for Black-Box LLM Personalization](https://mlsanity.com/paper/2406.02888/) (2024)
- [LLMs + Persona-Plug = Personalized LLMs](https://mlsanity.com/paper/2409.11901/) (2024)
- [PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agents](https://mlsanity.com/paper/2407.09394/) (2024)
- [A Survey of Lottery Ticket Hypothesis](https://mlsanity.com/paper/2403.04861/) (2024)
- [PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation](https://mlsanity.com/paper/2503.01303/) (2025)
- [Rethinking Graph Lottery Tickets: Graph Sparsity Matters](https://mlsanity.com/paper/2305.02190/) (2023)
- [Context Steering: Controllable Personalization at Inference Time](https://mlsanity.com/paper/2405.01768/) (2024)
- [Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation](https://mlsanity.com/paper/2408.03533/) (2024)
- [Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis](https://mlsanity.com/paper/2506.01262/) (2025)

## Built on by (most cited first, 5 of 5)

- [Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space](https://mlsanity.com/paper/2604.12016/) (2026)
- [Incoherent Values? Probing LLM Preferences Through Parametric Variation](https://mlsanity.com/paper/2606.21102/) (2026)
- [Steering Geometry: Validating Human Value Geometry in LLM Steering Space](https://mlsanity.com/paper/2609.06289/) (2026)
- [PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations](https://mlsanity.com/paper/2609.34571/) (2026)
- [RA2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning](https://mlsanity.com/paper/2610.19385/) (2026)

## Abstract (arXiv)

Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Existing approaches, however, typically adapt such behavior through external knowledge such as prompting, retrieval-augmented generation (RAG), or fine-tuning. We ask: do LLMs really need external context or parameters to adapt to different behaviors, or do they already have such knowledge embedded in their parameters? In this work, we show that LLMs already contain persona-specialized subnetworks in their parameter space. Using small calibration datasets, we identify distinct activation signatures associated with different personas. Guided by these statistics, we develop a masking strategy that isolates lightweight persona subnetworks. Building on the findings, we further discuss: how can we discover opposing subnetwork from the model that lead to binary-opposing personas, such as introvert-extrovert? To further enhance separation in binary opposition scenarios, we introduce a contrastive pruning strategy that identifies parameters responsible for the statistical divergence between opposing personas. Our method is entirely training-free and relies solely on the language model's existing parameter space. Across diverse evaluation settings, the resulting subnetworks exhibit significantly stronger persona alignment than baselines that require external knowledge while being more efficient. Our findings suggest that diverse human-like behaviors are not merely induced in LLMs, but are already embedded in their parameter space, pointing toward a new perspective on controllable and interpretable personalization in large language models.