Вид с высоты птичьего полета на райское побережье Мальдив
Утром 28 февраля Израиль нанес удар по Ирану и назвал его «превентивным». Атаку подтвердил министр обороны страны Исраэль Кац.
，更多细节参见下载安装汽水音乐
但同一時間，該劇繼續在海外走紅。2022年疫情期間的農曆新年，不少民眾選擇「宅在家」，台灣一個電視台於YouTube平台上24小時不間斷直播這部經典劇，觀眾一邊追劇，一邊在直播聊天室留言，成為了集體活動。，更多细节参见体育直播
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.
https://feedx.net