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.
Fanny Angelina Hesse, 1883.
，更多细节参见体育直播
Получивший взятку в размере 180 миллионов экс-мэр российского города обратился к суду14:53
2．“山野风”吹进多个餐饮赛道，品牌通过推副牌、开主题店方式入局山野餐饮是指以山野食材为主，通过营造山野场景和氛围的餐饮模式。其起源于20世纪80年代的“农家乐”，在2020年左右与“山系生活”理念融合，并在2025年进入爆发阶段，呈现出“万物皆可山野”的趋势，山野餐饮模式向火锅、烤肉、茶饮、地方菜等多个细分领域加速渗透。