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.
伊朗拟向通过霍尔木兹海峡的外国船舶收取费用的决定已引发美国主要石油公司的强烈抗议。多家企业高管已联合致信国务卿马可·鲁比奥与副总统JD·万斯，指出此类收费行为不应成为此前宣布的美伊两周停火协议的前提条件。
。WhatsApp 網頁版对此有专业解读
Rocco Fazzari/Getty Images
By subscribing, you consent to receive automated promotional text messages from Mashable Deals at the provided number. Standard message and data fees might apply. Maximum of two messages daily. Reply STOP to unsubscribe, or HELP for assistance. Subscription is not mandatory for purchases. Refer to our Privacy Policy and Terms of Use.