aiqbench analysis
Persona-Pruner addresses the computational bottleneck of running multiple AI NPCs by surgically isolating persona-specific sub-networks rather than relying on naive pruning methods. This approach significantly reduces resource costs while preserving role-playing fidelity and general capabilities, offering a practical path toward scalable virtual ecosystems. The work advances efficient machine learning architectures tailored for specialized character interactions without sacrificing performance.
Persona-Pruner: Sculpting Lightweight Models for Role-Playing
arXiv:2606.14695v2 Announce Type: replace-cross Abstract: Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona. However, applying these capabilities to real-world applications (e.g., ecosystems with numerous NPCs interacting simultaneously) exposes a critical inefficiency due to the excessive computational cost. In this paper, we question the necessity of dedicating a full, generalist model to a single persona, hypothesizing that a specific character identity relies on only a fraction of the model's total capacity. We observe that naively pruning LMs often severely degrades the role-playing performance for a specific persona; it does not distinguish between redundant knowledge and essential character traits. We propose Persona-Pruner, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description. Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art LLM pruning techniques, reducing the performance drop from the dense model by up to 93.8% over the strongest baseline on RoleBench in LLM-as-a-judge score, while still maintaining general LLM capabilities. Code is available at https://github.com/jsu-kim/Persona-Pruner.
Abstract:Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona. However, applying these capabilities to real-world applications (e.g., ecosystems with numerous NPCs interacting simultaneously) exposes a critical inefficiency due to the excessive computational cost. In this paper, we question the necessity of dedicating a full, generalist model to a single persona, hypothesizing that a specific character identity relies on only a fraction of the model's total capacity. We observe that naively pruning LMs often severely degrades the role-playing performance for a specific persona; it does not distinguish between redundant knowledge and essential character traits. We propose Persona-Pruner, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description. Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art LLM pruning techniques, reducing the performance drop from the dense model by up to 93.8% over the strongest baseline on RoleBench in LLM-as-a-judge score, while still maintaining general LLM capabilities. Code is available at this https URL.
Machine Learning (cs.LG); Computation and Language (cs.CL)
arXiv:2606.14695 [cs.LG]
(or arXiv:2606.14695v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.14695 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 275 words
Related coverage
Persona-Pruner: Sculpting Lightweight Models for Role-Playing
arXiv · Jun 15, 2026
LLMs + Persona-Plug = Personalized LLMs
arXiv · Jun 4, 2026
When Roleplaying, Do Models Believe What They Say?
arXiv · Jun 15, 2026
When Roleplaying, Do Models Believe What They Say?
arXiv · Jun 11, 2026