llms ai-agents personality-modeling natural-language-processing

Language Model Contains Personality Subnetworks

Your Language Model Secretly Contains Personality Subnetworks

arxiv.org

March 2, 2026

2 min read

🔥🔥🔥🔥🔥

44/100

Summary

Large Language Models (LLMs) exhibit the ability to adopt different personas and behaviors based on social context. This flexibility is achieved through the presence of personality subnetworks within the models, rather than relying solely on external knowledge or prompting methods.

Key Takeaways

Large Language Models (LLMs) contain persona-specialized subnetworks embedded in their parameter space, allowing them to adopt different behaviors without external context or parameters.
A masking strategy was developed to isolate lightweight persona subnetworks, revealing distinct activation signatures associated with different personas.
The method introduced is training-free and relies solely on the existing parameter space of the language model, demonstrating stronger persona alignment compared to baselines that require external knowledge.
The findings suggest that diverse human-like behaviors in LLMs are inherently embedded in their architecture, offering a new perspective on controllable and interpretable personalization.

Read original article

View story →