Fusian：多LoRA融合用于大语言模型中精细连续MBTI性格控制
Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models
AI总结：
本文提出Fusian框架，通过轨迹收集和基于强化学习的动态融合实现大语言模型中连续性格控制，实验显示其在性格控制精度上优于基线方法。
摘要：
大型语言模型（LLMs）在模拟多样化的人类行为和性格方面展现了 impressive 的能力。然而，现有性格控制方法，包括提示工程和标准监督微调（SFT），通常将性格特征视为离散类别（例如，'外向' vs. '内向'），缺乏对特征强度在连续谱上精确控制的能力。本文介绍Fusian，一种新的框架，用于在LLMs中实现细粒度连续性格控制。Fusian分为两个阶段：（1）轨迹收集，通过保存LoRA适配器序列捕获SFT期间性格采用的动态演变，有效映射特征的连续流形；（2）基于强化学习的动态融合，通过训练策略网络来动态计算这些冻结适配器的混合权重。通过从参数化由策略网络的狄利克雷分布中采样，Fusian将多个适配器融合以使模型输出与特定数值强度目标对齐。在Qwen3-14B模型上的实验表明，Fusian在性格控制精度上表现优异，显著优于基线方法在与用户指定特征强度对齐方面的表现。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
