P-React：通过专业化 LoRA 专家混合体合成人格特质的话题自适应反应
P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts
AI总结：
针对大五人格特质建模不足的问题，提出基于 MoE 与 PSL 的 P-React，并构建 OCEAN-Chat 数据集，实现跨话题一致、真实的个性化人格反应生成。
摘要：
个性化大语言模型（LLM）已在情感支持、角色扮演等众多应用中引起广泛关注。然而，现有工作主要聚焦于对显式角色档案进行建模，却忽视了真正塑造行为与决策的潜在人格特质，从而阻碍了更具拟人化特征且具备心理学依据的 AI 系统的发展。本文探讨大五人格特质的建模，该理论是心理学中应用最广泛的特质理论，并提出 P-React，这是一种基于专家混合（MoE）的个性化 LLM。具体而言，我们引入人格专业化损失（PSL），以更好地捕捉个体特质表达，提供更细致、更具心理学依据的人格拟像。为推动该领域研究，我们构建了 OCEAN-Chat，这是一个高质量、经人工验证的数据集，旨在训练 LLM 在多样话题中表达人格特质。大量实验证明了 P-React 在保持一致且真实的人格方面的有效性。
英文摘要：
Personalized large language models (LLMs) have attracted great attention in many applications, such as emotional support and role-playing. However, existing works primarily focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making, hampering the development of more anthropomorphic and psychologically-grounded AI systems. In this paper, we explore the modeling of Big Five personality traits, which is the most widely used trait theory in psychology, and propose P-React, a mixture of experts (MoE)-based personalized LLM. Particularly, we integrate a Personality Specialization Loss (PSL) to better capture individual trait expressions, providing a more nuanced and psychologically grounded personality simulacrum. To facilitate research in this field, we curate OCEAN-Chat, a high-quality, human-verified dataset designed to train LLMs in expressing personality traits across diverse topics. Extensive experiments demonstrate the effectiveness of P-React in maintaining consistent and real personality.
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。
