Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models

2026-03-16

AI Summary

This work addresses the limitation of existing personality control methods for large language models, which typically model personality traits as discrete categories and thus struggle to enable continuous, fine-grained modulation of trait intensity. To overcome this, we propose Fusian, a novel framework that first constructs a continuous manifold of personality traits through trajectory collection and then employs a reinforcement learning–driven dynamic fusion strategy to weight and combine multiple frozen LoRA adapters, precisely aligning with user-specified personality intensity targets. Fusian is the first approach to achieve accurate, numerically continuous control over personality strength, breaking away from conventional discrete modeling paradigms. The introduced RL-driven dynamic multi-LoRA fusion mechanism substantially enhances the nuance and controllability of personality expression. Experiments on Qwen3-14B demonstrate that Fusian significantly outperforms current baselines.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Large Language Models (LLMs) have demonstrated impressive capabilities in simulating diverse human behaviors and personalities. However, existing methods for personality control, which include prompt engineering and standard Supervised Fine-Tuning (SFT), typically treat personality traits as discrete categories (e.g., "Extroverted" vs. "Introverted"), lacking the ability to precisely control the intensity of a trait on a continuous spectrum. In this paper, we introduce Fusian, a novel framework for fine-grained, continuous personality control in LLMs. Fusian operates in two stages: (1) Trajectory Collection, where we capture the dynamic evolution of personality adoption during SFT by saving a sequence of LoRA adapters, effectively mapping the continuous manifold of a trait; and (2) RL-based Dynamic Fusion, where we train a policy network using Reinforcement Learning to dynamically compute mixing weights for these frozen adapters. By sampling from a Dirichlet distribution parameterized by the policy network, Fusian fuses multiple adapters to align the model's output with a specific numerical target intensity. Experiments on the Qwen3-14B model demonstrate that Fusian achieves high precision in personality control, significantly outperforming baseline methods in aligning with user-specified trait intensities.

Problem

• personality control
• continuous traits
• Large Language Models
• fine-grained control
• MBTI

Innovation

• Multi-LoRA Fusion
• Continuous Personality Control
• Reinforcement Learning
• LoRA Adapters
• Dirichlet Distribution