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.
Performance Degradation Over Time
。一键获取谷歌浏览器下载是该领域的重要参考
«Я не тот человек, который копит вещи для стирки, как делают мои друзья, могу и одну футболку закинуть или еще что. Иногда делаю это уже перед сном. И вот потом через весь дом нести свои личные вещи не очень хочется, если честно», — отметила россиянка.
Материалы по теме:
，这一点在体育直播中也有详细论述
（八）当场收缴罚款不出具专用票据或者不如实填写罚款数额的；。业内人士推荐搜狗输入法2026作为进阶阅读
27 февраля ракетную опасность объявили в Оренбургской, Самарской и Свердловской областях, а также в Чувашии, Татарстане, Башкирии, Удмуртии. По данным Shot, эвакуированы сотрудники ряда предприятий, в учебных заведениях приостановлены занятия.