PersonaFuse：一个用于增强人机LLM交互的人格激活驱动框架
PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions
AI总结：
本文提出PersonaFuse框架，通过混合专家架构结合人格适配器与动态路由网络，使LLMs能根据情境表达不同人格，在不牺牲推理能力和安全性的前提下显著提升了社交情感智能及下游应用表现。
摘要：
大型语言模型（LLMs）的最新进展在各个领域展现出卓越的能力。这些发展促使人类与LLMs在社交陪伴和心理支持等各种情境下进行更直接的交流。然而，LLMs在真实对话中常表现出情感感知和社交能力的局限。这些局限部分源于它们无法根据不同的社交和任务情境调整交流风格与情感表达。在本研究中，我们提出了PersonaFuse，一种新颖的LLM后训练框架，使LLMs能够针对不同情境适应并表达不同人格。受特质激活理论和大五人格模型启发，PersonaFuse采用混合专家架构，将人格适配器与动态路由网络相结合，实现情境化的特质表达。实验结果表明，PersonaFuse在社交情感智能的多个维度上显著优于基线模型。重要的是，这些提升是在不牺牲通用推理能力或模型安全性的前提下实现的，而通用推理能力和模型安全性受损正是直接提示和监督微调方法的常见局限。PersonaFuse还在心理健康咨询和基于评论的客户服务等下游以人为中心的应用中提供了一致的改进。最后，针对GPT-4o和DeepSeek等领先LLMs的人类偏好评估表明，尽管PersonaFuse的模型规模相对较小，但其响应质量具有竞争力。这些发现表明，PersonaFuse为开发社交情感增强的LLMs提供了一种理论基础扎实且实用的方法，标志着向更加以人为中心的AI系统迈出了重要一步。
英文摘要：
Recent advancements in Large Language Models (LLMs) demonstrate remarkable capabilities across various fields. These developments have led to more direct communication between humans and LLMs in various situations, such as social companionship and psychological support. However, LLMs often exhibit limitations in emotional perception and social competence during real-world conversations. These limitations partly originate from their inability to adapt their communication style and emotional expression to different social and task contexts. In this work, we introduce PersonaFuse, a novel LLM post-training framework that enables LLMs to adapt and express different personalities for varying situations. Inspired by Trait Activation Theory and the Big Five personality model, PersonaFuse employs a Mixture-of-Expert architecture that combines persona adapters with a dynamic routing network, enabling contextual trait expression. Experimental results show that PersonaFuse substantially outperforms baseline models across multiple dimensions of social-emotional intelligence. Importantly, these gains are achieved without sacrificing general reasoning ability or model safety, which remain common limitations of direct prompting and supervised fine-tuning approaches. PersonaFuse also delivers consistent improvements in downstream human-centered applications, such as mental health counseling and review-based customer service. Finally, human preference evaluations against leading LLMs, including GPT-4o and DeepSeek, demonstrate that PersonaFuse achieves competitive response quality despite its comparatively smaller model size. These findings demonstrate that PersonaFuse offers a theoretically grounded and practical approach for developing social-emotional enhanced LLMs, marking a significant advancement toward more human-centric AI systems.
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。
