Abstract:Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Existing approaches, however, typically adapt such behavior through external knowledge such as prompting, retrieval-augmented generation (RAG), or fine-tuning. We ask: do LLMs really need external context or parameters to adapt to different behaviors, or do they already have such knowledge embedded in their parameters? In this work, we show that LLMs already contain persona-specialized subnetworks in their parameter space. Using small calibration datasets, we identify distinct activation signatures associated with different personas. Guided by these statistics, we develop a masking strategy that isolates lightweight persona subnetworks. Building on the findings, we further discuss: how can we discover opposing subnetwork from the model that lead to binary-opposing personas, such as introvert-extrovert? To further enhance separation in binary opposition scenarios, we introduce a contrastive pruning strategy that identifies parameters responsible for the statistical divergence between opposing personas. Our method is entirely training-free and relies solely on the language model's existing parameter space. Across diverse evaluation settings, the resulting subnetworks exhibit significantly stronger persona alignment than baselines that require external knowledge while being more efficient. Our findings suggest that diverse human-like behaviors are not merely induced in LLMs, but are already embedded in their parameter space, pointing toward a new perspective on controllable and interpretable personalization in large language models.
Мэр города занялась сексом с 16-летним подростком на глазах у своих детей02:00
，这一点在同城约会中也有详细论述
[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z]{2,4}$(446 239)
“If your differentiation lives mostly in UI [user interface] and automation, that’s no longer enough,” he said. “The barrier to entry has dropped, which makes building a real moat much harder.”
在无障碍环境建设中，很多城市都存在类似问题。中国助残志愿者协会智库专家、北京大学建筑与景观设计学院副教授李迪华和团队2024年3月至2025年底，对北京、上海、深圳、广州、武汉、长沙等地的无障碍卫生间展开调研，结果令人担忧。