超越静态人设：面向大语言模型的情境性人格引导
Beyond Static Personas: Situational Personality Steering for Large Language Models
AI总结：
本文提出IRIS框架，通过分析人设神经元揭示情境依赖性，实现无训练的神经元引导方法，在PersonalityBench和SPBench上验证了其在复杂情境下的泛化与鲁棒性。
摘要：
个性化大语言模型（LLMs）能促进更自然的人类样互动。然而，现有个性化方法受限于可控性差和资源消耗大，且依赖静态人格建模限制了在不同情境下的适应性。为解决这些问题，我们通过多视角分析人设神经元，揭示了LLM人格中情境依赖性和一致的情境-行为模式。基于这些见解，我们提出了IRIS，一种无需训练的基于神经元的Identify-Retrieve-Steer框架，用于高级情境性人格引导。我们的方法包括情境人设神经元识别、情境感知神经元检索和相似性加权引导。我们在PersonalityBench和新引入的SPBench上实验证明了框架的有效性。实验结果表明，我们的方法超越了最佳基线，展示了IRIS在复杂、未见情境和不同模型架构中的泛化能力和鲁棒性。
英文摘要：
Personalized Large Language Models (LLMs) facilitate more natural, human-like interactions in human-centric applications. However, existing personalization methods are constrained by limited controllability and high resource demands. Furthermore, their reliance on static personality modeling restricts adaptability across varying situations. To address these limitations, we first demonstrate the existence of situation-dependency and consistent situation-behavior patterns within LLM personalities through a multi-perspective analysis of persona neurons. Building on these insights, we propose IRIS, a training-free, neuron-based Identify-Retrieve-Steer framework for advanced situational personality steering. Our approach comprises situational persona neuron identification, situation-aware neuron retrieval, and similarity-weighted steering. We empirically validate our framework on PersonalityBench and our newly introduced SPBench, a comprehensive situational personality benchmark. Experimental results show that our method surpasses best-performing baselines, demonstrating IRIS's generalization and robustness to complex, unseen situations and different models architecture.
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。
