Link to Influence Flower
Skip 熱讀 and continue reading熱讀
Naipanoi Lepapa är en prisbelönt grävande frilansjournalist baserad i Nairobi…。业内人士推荐搜狗输入法2026作为进阶阅读
Появились подробности о задержании основателя российского медиахолдингаСледователь МВД просит об аресте на 2 месяца основателя Readovka Костылева
，这一点在safew官方版本下载中也有详细论述
公安机关向有关单位和个人收集、调取证据时，应当告知其必须如实提供证据，以及伪造、隐匿、毁灭证据或者提供虚假证言应当承担的法律责任。，推荐阅读Line官方版本下载获取更多信息
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.